Speech Client Configuration (client_property.conf)

This file controls settings related to the speech client. This configuration file controls the bulk of functionality for speech recognition options.

It is located by default in mrcp-api/docker/lumenvox .

The following parameters can be set. The format to use within the configuration file is PROPERTY_NAME = VALUE

[GLOBAL]

 This section contains global configuration settings for both SRE (Speech Engine) and TTS (text-to-speech server).

VERSION

Description: Contains information about the version of the software that created the configuration file. Do not modify this.

Possible Values: This should not be modified by users. 

LICENSE_SERVERS

Description: The IP address or host-name and (optionally) the port of the License Server to use. 

Possible Values: A string of IP addresses or host-names followed optionally by a colon and a port number, separated by semicolons. E.g. you could specify 127.0.0.1:7569;10.0.0.1:4971 to use two License Servers -- the first at 127.0.0.1 and port 7569, the second at 10.0.0.1 on port 4971.

Default Value: 127.0.0.1:7569  ( license server on local machine )

Note: Prior to the 10.0 release of the software, this property was known as LIC_SERVER_HOSTNAME 

LICENSE_CACHE_PERIOD

Description: Licenses acquired from a license server during port creation are normally released back to the license server when the port is destroyed. License caching mechanism, when enabled, prevents such licenses from being released back to the license server during port destruction. Instead, it is held in a cache and will be reused during a subsequent port creation. This setting controls the duration for which such a license will be held in cache. If the cached license doesn't get reused before this period elapses, it is then released back to the license server automatically. This helps improve performance by reducing the amount of communication with the license server. 

Specifies the amount of time (in seconds) a released license is to be cached for use by future license requests.

Possible Values: A positive integer (max 3600); 0 disables caching.

Default Value: 30 (seconds)

 Note: To disable license caching, set the value to zero. 

LOGGING_VERBOSITY

Description: Controls the verbosity of event logging. This can be used to increase or decrease the amount of information logged by the application. Note that increasing the logging verbosity causes increase in CPU usage, and should therefore be avoided wherever possible in a production environment where optimal performance is critical.  

Possible Values: 1 - 4

• 1 = Minimal logging. Logs only errors and critical issues.
• 2 = Medium logging. Logs all non-debug information, includes types covered in Minimal logging as well.
• 3 = Maximum logging. Logs most types of events. This will include any and all informational and debugging activity.
• 4 = Diagnostic Logging. Logs all types of events. This will include diagnostic information that may be useful to LumenVox support staff

Default Value: 1  ( minimal logging )

SSL_VERIFYPEER

Description: Enables or disables the verification of a peer's certificate using a local certificate authority file upon HTTPS requests. Set to 0 (disabled) to skip verification for trusted sites. 

Possible Values:

• 0 = Disable verification.
• 1 = Enable verification.

Default Value: 1  ( verification enabled ) 

CERTIFICATE_AUTHORITY_FILE

Description: The path to the file used to verify peer certificates upon HTTPS requests. This file may contain one or more certificate authority (CA) certificates. Set to an empty string to use default CA certificates file. 

Possible Values: A local file system path to CA certificate file in PEM format

Default Value:  (empty string - use default CA certificate)

[SRE]

 This section contains configuration settings for use with the Speech Recognition Engine. 

SRE_SERVERS

Description: This property sets which Speech Engine servers are used for processing decodes. 

After initialization, this value can be changed using PROP_EX_SRE_SERVERS when calling SetPropertyEx from the client application.

Possible Values: A list of IP addresses and optional ports separated by semicolons. For instance, 127.0.0.1;10.0.0.1:5721 specifies a server at 127.0.0.1 using the default port of 5730, and a server at 10.0.0.1 using the port 5721.  

Default Value: 127.0.0.1  ( ASR on local machine )

LICENSE_TYPE

Description: The default license type to use when creating a port. 

Possible Values: 

• Auto
• SLM
• SpeechPort
• VoxLite
• CPA
• AMD

If the value is set to Auto, the client will auto-pick the license between SpeechPort and VoxLite. It will use up SpeechPort licenses before using VoxLite licenses. 

If the value is set to SpeechPort, the client will get the license from the SpeechPort license pool. 

If the value is set to VoxLite, the client will get the license from the VoxLite license pool (these licenses only allow up to 500 vocabulary items per recognition). 

SLM, CPA and AMD licenses are set to use their respective functionality.

After initialization, this value can be changed using PROP_EX_LICENSE_TYPE when calling SetPropertyEx from the client application.

Default Value: Auto 

DELAYED_LICENSE_ACQUISITION

Description: When this option is enabled, it allows license acquisition to be delayed until a call to LoadGrammar is made. Enabling this mode is not recommended unless using call progress analysis (CPA).

Possible Values:

• 0 - Disabled
• 1 - Enabled

Default Value: 0  ( delayed license acquisition disabled )

MAX_NBEST_RETURNED

Description: Specifies the maximum number of n-best results to be returned by the Engine.

After initialization, this value can be changed using PROP_EX_MAX_NBEST_RETURNED when calling SetPropertyEx from the client application.

Possible Values: Number of n-best results. Integer from 0 - 10000

Default Value: 1 

DECODE_TIMEOUT

Description: In a non-blocking decode, this is the timeout value, in milliseconds, used by LV_SRE_WaitForDecode and LVSpeechPort::WaitForDecode functions. In blocking decode, this is the time to wait until the decode times out and returns an error from LV_SRE_Decode and LVSpeechPort::Decode.

After initialization, this value can be changed using PROP_EX_DECODE_TIMEOUT when calling SetPropertyEx from the client application.

Possible Values: Integer time in milliseconds from 0 - 10000000.

Default Value: 20000  ( 20 seconds )

LOAD_GRAMMAR_TIMEOUT

Description: Specifies how long, in milliseconds, the client should wait for a grammar to load. If the timeout is reached before the grammar is loaded, the LoadGrammar function returns error code -37, LV_LOAD_GRAMMAR_TIMEOUT.

After initialization, this value can be changed using PROP_EX_LOAD_GRAMMAR_TIMEOUT when calling SetPropertyEx from the client application.

Possible Values: Integer time in milliseconds from 1000 - 2147483647 (approx. 600 hours).

Default Value: 200000  ( 200 seconds )

PARSE_GRAMMAR_TIMEOUT

Description: Specifies how long, in milliseconds, the client should wait for a grammar to parse. If the timeout is reached before the grammar is parsed, the LoadGrammar function returns error code -6, LV_TIME_OUT.

Possible Values: Integer time in milliseconds from 0 - 10000000 (approx. 166 minutes).

Default Value: 10000  ( 10 seconds )

STRICT_SISR_COMPLIANCE

Description: Controls whether LumenVox will strictly implement the final SISR 1.0 standard for adding tags to grammars. Unless this value is changed, LumenVox normally runs in strict mode, using the final SISR 1.0 standard unless the grammar's tag-format is declared as lumenvox/1.0. If strict compliance is disabled, then LumenVox will treat a tag-format declaration of semantics/1.0 in a backwards compatibility mode, using the older draft of SISR.

After initialization, this value can be changed using PROP_EX_STRICT_SISR_COMPLIANCE when calling SetPropertyEx from the client application.

Possible Values:

• 0 (disabled)
• 1 (enabled)

Default Value: 1  ( strict SISR compliance enabled )

TRIM_SILENCE_VALUE

Description: Controls how aggressively the Engine trims leading silence from input audio. 

After initialization, this value can be changed using PROP_EX_TRIM_SILENCE_VALUE when calling SetPropertyEx from the client application.

Possible Values: A number ranging from 0 (very aggressive) to 1000 (no silence trimmed).

Default Value: 970 

SAVE_SOUND_FILES

Description: Controls whether the application will save off .callsre files used with the LumenVox Speech Tuner. 

Turn this on to capture audio and more information related to each decode. These files will be saved by default to/var/log/lumenvox/client/responses/ on Linux and C:\Program Files\LumenVox\Engine\Lang\Responses\ on Windows. See the Logging Call Files knowledgebase article for additional details. 

After initialization, this value can be changed using PROP_EX_SAVE_SOUND_FILES when calling SetPropertyEx from the client application.

Possible Values: 0 - 3

• 0 = NONE
• 1 = BASIC
• 2 = ADVANCED
• 3 = ALL

Default Value: 0 

NOISE_REDUCTION_ENABLE

Description: Specifies the Noise Reduction Model to be used by the Engine. 

These settings can be used to strip out background noise in audio being processed by the Engine. For most users the default noise reduction algorithm should work best. For certain noise conditions the Alternate noise reduction algorithm has shown better results. Hence, advanced users can try switching the algorithm to see if it improves their performance in noisy conditions. The Adaptive noise reduction algorithm works best only when the noise is constantly changing such as car or highway noise. For more stationary noises like fan noise, the default algorithm will show the best performance.

After initialization, this value can be changed using PROP_EX_NOISE_REDUCTION_ENABLE when calling SetPropertyEx from the client application.

Possible Values: 0 - 3

• 0 = No Noise Reduction. Deactivates noise reduction. This setting is not recommended unless you actually find a problem with noise reduction since disabling this will increase decode times during the presence of noise.
• 1 = Default. This is the recommended Advanced Noise Reduction algorithm for most cases, which is automatically activated when noise levels are high enough to require noise reduction.
• 2 = Alternate. This is the alternate Noise Reduction algorithm that can be tested if the performance with the default setting is not satisfactory. This is similar to the default setting, but we have seen varied results based on differing noise types and levels. For most noise types, the default algorithm should work better, however certain noise types and/or applications may benefit from this setting.
• 3 = Adaptive. The Advanced Adaptive Noise Reduction algorithm continually estimates the noise to be effective in continuously changing noisy environments. This works better than the default setting when there is car noise and other continuously changing noises. For stationary/constant noises like line noise, the performance is slightly lower than the Default Advanced Noise Reduction.

Default Value: 1 

CLIENT_CACHE_ENABLE

Description: Enable or disables client side (Speech Port) grammar caching. 

This can significantly reduce grammar load times, since processing of grammars is cached in memory and disk, improving performance.  

 Possible Values: 

• 0 (caching disabled)
• 1 (enabled)

Default Value: 1 

CLIENT_CACHE_EXPIRATION

Description: The amount of time, in minutes, to allow an unused grammar to remain in memory. After a grammar has remained unused for this period of time, it will be unloaded from memory, but will remain in the disk cache, allowing fast reactivation and reloading if needed. 

Possible Values: A number between 2 (minimum) and 1,000,000 (maximum) in minutes

Default Value: 1440 (1 day)

CLIENT_CACHE_MAX_NUMBER

Description: The maximum number of cached grammar entries to hold in memory at any time. 

Possible Values: A number between 2 (minimum) and 100,000 (maximum) 

Default Value: 100 

CLIENT_CACHE_MAX_MEMORY

Description: The maximum size of memory to utilize for caching grammars. 

Possible Values: A number of bytes between 100,000 (min) and 536,870,912 (max)

Default Value: 268435456 (256 MB)

SECURE_CONTEXT

 Description: This functionality controls the ability to suppress potentially sensitive information that may exist in log files and call logs. Suppressed data includes both text and audio

 Note that in this [ASR] section, this value controls the ASR log suppression, there is a corresponding value in the [TTS] section below

 After initialization, this value can be changed using PROP_EX_SECURE_CONTEXT when calling SetPropertyEx from the client application.

 Possible Values: 

• 0 - Normal (unsuppressed logging)
• 1 - Suppressed logging

Default Value: 0

LOGGING_ENCRYPTION_KEY

Description: This functionality allows users to specify which certificate(s), if any, should be used during encryption. This is a list of public key/certificate files to be used for callsre encryption, consisting of a comma delimited list of URLs pointing to certificate files. When encryption is enabled, the callsre events will be encrypted using each certificate.

Possible Values: blank, or comma delimited list of certificate URLs

Default Value:  ( blank - no encryption certificates specified )

LOGGING_ENCRYPTION_LEVEL

Description: This functionality controls the level of encryption to use on the callsre files.

Possible Values:  

• 0 No encryption
• 1Just text related to recognition and TTS text
• 2 Same as 1, including `external tags`
• 3Same as 2, including grammars
• 4 Same as 3, including audio
• 5 Same as 4, but `external tags` are NOT encrypted
• 10 Whole file

Default Value: 0  ( no encryption )

MENU_ID_STRING_MODE

Description: This setting specifies the information used to determine the uniqueness of an active grammar set. This is typically used in conjunction with the Speech Tuner and provides a means of determining uniqueness of an active grammar set, allowing the Speech Tuner to automatically discover menus and grammars sets so that data can be organized more naturally using these constructs.

Possible Values:  

• 0 Don't log menu ID string (backward compatible behavior)
• 1 Use grammar URIs and labels
• 2 Use grammar URIs only (default)
• 3 Use grammar labels only
• 4 Use grammar URIs and labels and hashcodes

Default Value: 2  ( use grammar URIs only )

ASR_RESULT_DETAIL_ENABLE

Description: This specifies if the transcription result will include extra details including word level timing and confidence scores.

Possible Values:  

• 0 Details are not returned.
• 1 Extra word level timing and confidence scores are returned within the interpretation results.

Default Value: 0  

[TTS]

 This section contains global configuration settings for the text-to-speech server. Note that many of these settings will not be used by most users and are included in order to reflect the requirements of the Speech Synthesis Markup Language (SSML)standard. Users interested in more information about the various prosody settings would be advised to read the specification for the standard.

TTS_SERVERS

Description: This property sets which TTS Servers Engine servers are used for processing TTS syntheses

Note that in LumenVox versions prior to 15.1, additionally specified TTS Servers in this field were used in failover situations, where each successive entry would be used in the event of failure of previously listed servers. Starting with LumenVox 15.1, all specified servers will be accessed in a round-robin manner, which allows TTS synthesis requests to be distributed across all defined TTS Servers.

Please also note that in all versions, you should ensure that the configuration of voices installed on all defined TTS Servers be identical to avoid any failures when synthesis requests are made.

Possible Values: A list of IP addresses and optional ports separated by semicolons. For instance, 127.0.0.1;10.0.0.1:5721 specifies a server at 127.0.0.1 using the default port of 7579, and a server at 10.0.0.1 using the port 5721. 

Default Value: 127.0.0.1  ( use TTS server on local machine )

SYNTHESIS_LANGUAGE

Description: The default language to use for synthesis. 

Possible Values: A valid language and country code. Languages are two letters and lowercase and a country code is two letters and uppercase. You will need a license for this language and the language pack installed on the TTS server(s) in order to get synthesis with the specified language.

Default Value: en-US

SYNTH_VOICE_GENDER

 Description: The gender of the voice that will be used for synthesis.  

 Possible Values: Either neutral (which uses the default), male, or female. 

 Default Value: neutral 

SYNTH_VOICE_NAME 

 Description: The name of the voice to be used in the synthesis.  

 Possible Values: A name of a valid TTS voice. This will vary depending on the TTS licenses and voice packs you have installed. If left blank, it will default to the first voice for which the system has a license and an installed voice pack. 

 Default Value:  ( blank - use first licensed voice located )

SYNTHESIS_SOUND_FORMAT

 Description: The default codec/format for the synthesized audio.  

 Possible Values: A value from 1 to 3, representing the following values: 

• 1 - ULAW
• 2 - PCM
• 3 - ALAW

Default Value: 1  ( ulaw format )

TTS_REQUEST_TIMEOUT

 Description: The amount of time to wait, in milliseconds, for a response from the TTS Server after sending a request for speech synthesis. 

If you process unusually long segments of TTS, you may wish to extend this value, however this does reflect the length of the audio produced, simply the amount of time to wait for synthesis to complete, which is typically many times faster than real-time. 

 Possible Values: An amount of time, in milliseconds. 

 Default Value: 10000  ( 10 seconds )

SYNTHESIS_SAMPLING_RATE

 Description: The default sampling rate (in Hz) to use for synthesized speech.

 Possible Values: A valid sampling rate. You will need the appropriate license(s) to use voices of the selected sample rate.

• 8000     ( 8 kHz, telephony quality )
• 22050  ( 22 kHz higher quality )

Default Value: 8000  ( 8 kHz )

LOG_TTS_EVENTS

 Description: Whether the application will generate TTS event log files for use with the Speech Tuner. Similar to the SAVE_SOUND_FILES option for Speech events.  

 Possible Values: 

• 0 - Disable
• 1 - Enable

 Default Value: 0  ( TTS logging disabled )

SYNTH_PROSODY_PITCH

 Description: The pitch of the audio being synthesized. 

 Possible Values: A number followed by "Hz", a relative change, or one of the following values: "x-low", "low", "medium", "high", "x-high", or "default". See the SSML standard for more detail. 

 Default Value: default

SYNTH_PROSODY_CONTOUR

 Description: The contour of the audio being synthesized.  

 Possible Values: Please refer to  the SSML standard on pitch contour for details. 

 Default Value: blank to use the default setting 

SYNTH_PROSODY_RANGE

 Description: The range of the audio being synthesized.  

 Possible Values: A number followed by "Hz", a relative change, or one of the following values: "x-low", "low", "medium", "high", "x-high", or "default". See the SSML standard for more detail.

 Default Value: default 

SYNTH_PROSODY_RATE

 Description: The speaking rate of the audio being synthesized.  

 Possible Values: A relative change or "x-slow", "slow", "medium", "fast", "x-fast", or "default". See the SSML standard for more detail. 

 Default Value: default 

SYNTH_PROSODY_DURATION

 Description: The duration of time it will take for the synthesized text to play.  

 Possible Values: A time, such as "250ms" or "3s". 

 Default Value: default 

SYNTH_PROSODY_VOLUME

 Description: The volume of the audio being synthesized.  

 Possible Values: A number, a relative change or one of: "silent", "x-soft", "soft", "medium", "loud", "x-loud", or "default". See the SSML specification for more information. 

 Default Value: default 

SYNTH_VOICE_AGE

 Description: The age of the voice used for synthesis.  

 Possible Values: A non-negative integer. 

 Default Value: default 

SYNTH_VOICE_VARIANT

 Description: The preferred voice variant to be used in the synthesis.  

 Possible Values: 

 Default Value: default 

SYNTH_EMPHASIS_LEVEL

 Description: The strength of the emphasis used in the voice during synthesis.  

 Possible Values: One of: "strong", "moderate", "none" or "reduced". 

 Default Value: moderate

SECURE_CONTEXT

Description: This functionality controls the ability to suppress potentially sensitive information that may exist in log files and call logs. Suppressed data includes both text and audio.

Note that in this [TTS] section, this value controls the TTS log suppression, there is a corresponding value in the [ASR] section above

Possible Values: 

• 0 - Normal (unsuppressed logging)
• 1 - Suppressed logging 

Default Value: 0  ( unsuppressed logging )

VISEME_GENERATION

Description: This functionality controls TTS viseme generation during synthesis. These may be useful when running applications requiring lip-sync information 

Possible Values: 

• 0 - visemes disabled
• 1 - visemes enabled 

Default Value: 0  ( visemes disabled )

[STREAM]

This section contains configuration settings for the streaming interface.  Note that most users will generally adopt the default settings for these items, since they can affect overall accuracy if set incorrectly.

See the Stream Properties article for more details on using some of these settings.

BARGE_IN_TIMEOUT

Description: The streaming interface will flag STREAM_STATUS_BARGE_IN_TIMEOUT, if no speech was detected in the number of milliseconds specified by this property.

Possible Values: -1 (infinite) or a positive integer number of milliseconds 

Default Value: -1  ( infinite )

END_OF_SPEECH_TIMEOUT

Description: After barge-in, the streaming interface will flag STREAM_STATUS_END_SPEECH_TIMEOUT, if it did detect end-of-speech in the time specified by this property. This is different from the end of speech delay; STREAM_PARM_END_OF_SPEECH_TIMEOUT represents the total amount of time a caller has to speak after barge-in is detected.

Possible Values: An amount of time, in milliseconds. -1 = Infinite

Default Value: -1  ( infinite )

VAD_BARGEIN_THRESHOLD

Description: A higher value makes the VAD more sensitive towards speech, and less sensitive towards non-speech, which means that the VAD algorithm must be more sure that the audio is speech before triggering barge in. 

Raising the value will reject more false positives/noises. However, it may mean that some speech that is on the borderline may be rejected. This value should not be changed from the default without significant tuning and verification.

Possible Values: Integer range from 0 to 100

Default Value: 50 

VAD_STREAM_INIT_DELAY

Description: Accurate VAD depends on a good estimation of the acoustic environment. The VAD module uses the first couple frames of audio to estimate the acoustic environment, such as noise level. The length of this period is defined by this parameter.

Possible Values: A positive integer number of milliseconds.

Default Value: 100  ( milliseconds )

VAD_EOS_DELAY

Description: This is the amount of time, specified in milliseconds, that the Engine must detect silence after speech before it begins processing the utterance.

Possible Values: A positive integer number of milliseconds

Default Value: 800  ( milliseconds )

VAD_WIND_BACK

Description: The length of audio to be wound back at the beginning of voice activity. This is used primarily to counter instances where barge-in does not accurately capture the very start of speech. The resolution of this parameter is 1/8 of a second.

Possible Values: A positive integer number of milliseconds

Default Value: 480  ( milliseconds )

VAD_SNR_SENSITIVITY

Description: Determines how much louder the speaker must be than the background noise in order to trigger barge-in. The smaller this value, the easier it will be to trigger barge-in.

Possible Values: Integer range from 0 to 100

Default Value: 50  

VAD_VOLUME_SENSITIVITY

Description: The volume required to trigger barge-in. The smaller the value, the more sensitive barge-in will be. This is primarily used to deal with poor echo cancellation. By setting this value higher (less sensitive) prompts that are not properly canceled will be less likely to falsely cancel barge-in.

Possible Values: Integer range from 0 to 100

Default Value: 50  

AUTO_DECODE

Description: If active, the decode will start immediately on end-of-speech detection or a call to StopStream. Otherwise, the application needs to call LV_SRE_Decode to begin a decode.

Possible Values: 0 - 1

• 0 - Off (Auto-decode disabled)
• 1 - On (Auto-decode enabled)

Default Value: 0  ( auto-decode disabled )

SOUND_FORMAT

Description: The sound format handled by the stream.

Possible Values: 1 - 4

• 1 - ULAW_8KHZ
• 2 - PCM_8KHZ
• 3 - PCM_16KHZ
• 4 - ALAW_8KHZ

Default Value: 1  ( ulaw 8kHz )

VOICE_CHANNEL

Description: The voice channel for decode to load the sound data to once end-pointing is done.

Possible Values: Integer range from 0 to 63

Default Value: 0  

CPA_HUMAN_RESIDENCE_TIME

Description: Used in Call Progress Analysis (CPA) Mode. If we cannot verify the CPA mode through ASR but the length of speech detected is below this length, it is considered to be a human residence.

Possible Values: A positive integer number of milliseconds

Default Value: 1800  ( milliseconds )

CPA_HUMAN_BUSINESS_TIME

Description: Used in Call Progress Analysis (CPA) Mode. If we cannot verify the CPA mode through ASR but the length of speech detected is below this length, but above the length of human residence we consider it to be a human business

Possible Values: A positive integer number of milliseconds

Default Value: 3000  ( milliseconds )

CPA_UNKNOWN_SILENCE_TIMEOUT

Description: Used in Call Progress Analysis (CPA) Mode.  If we do not barge-in by this time we return with an Unknown Speech in the answer. This is very similar to a Barge-in-timeout, however, a barge-in-timeout leads to the Barge-in-timeout callback being called. The CPA_UNKNOWN_SILENCE_TIMEOUT leads to the Unknown Silence answer being returned by a decode request in CPA mode.

Possible Values: A positive integer number of milliseconds

Default Value: 5000  ( milliseconds )

[GRAMMAR]

This section contains configuration settings associated with grammar processing. 

LANGUAGE

Description: The default language set for loaded grammars if not otherwise specified.

Possible Values: language specifier string as found in an SRGS grammar. ASR Phoneme Tables for a list of supported options

Default Value: en-US

MODE

Description: The default grammar mode for loaded grammars if not otherwise specified.

Possible Values:

• voice
• dtmf

Default Value: voice

TAG-FORMAT

Description: The default tag-format for loaded grammars if not otherwise specified.

Possible Values: Supported tag-formats including

• lumenvox/1.0
• semantics/1.0
• semantics/1.0-literals
• semantics/1.0.2006
• semantics/1.0.2006-literals

Default Value: lumenvox/1.0 

BASE_URI

Description: The default base path for loaded grammars if not otherwise specified. An empty string specifies the current working directory to be used.

Possible Values: Any valid URL

Default Value:  ( blank : use current working directory )

FETCH-TIMEOUT

Description: The default cache control setting for loaded grammars if not otherwise specified. An empty string specifies no timeout.

Possible Values: A positive integer number of milliseconds from 0 - 10000000, or an empty string specifies no timeout.

Default Value: 60000  ( one minute )

GRAMMAR_ENGINE

Description: This specifies the default behavior for  which engine should handle ASR requests.  This can be over ridden via META tags within the grammar.

Possible Values:  

• 0 Use the DNN engine preferentially.  If no DNN ASR server is available to handle the request, it will attempt to use the Legacy engine, if available
• 1 Use the legacy ASR engine only
• 2 Use the DNN ASR engine only

Default Value: 0