Release notes 4.4.0

Release date: 31st October 2023

Summary

This page highlights all the changes, new features and bugs addressed within the LumenVox Containers version 4.4.0 release. This change affects Speech products. This version is not available for Voice biometric products, this will be made available in upcoming releases.

Highlights

Improvements to stability, performance and load handling
New finalize API introduced
code change for cleanup scripts
Redis TTL now configurable (new default 3 hours)
Partial results available on Transcription (gRPC)
Redis updated to 7.0.0
Enhancements to MRCP
Enhancements to the analysis portal

*Note: For TTS, we recommend that text not exceed 4mb (this is roughly 1300 Characters with spaces or around 250 words)

**Note: For Transcription, we recommend that users not exceed 90 minutes of transcribed audio due to gRPC size limits.

What’s new on LumenVox Cloud 4.4.0

New Features

New finalize API implemented for the following products:
- ASR streaming mode
- Transcription streaming mode
- Transcription - continuous streaming mode
- Transcription - enhanced streaming mode
- AMD
Partial results available for Transcription
TTL for Redis has been made configurable

Updates

Improvements have been made to the following:
- Stability, performance and load handling
- Analysis portal updated with the following:
  - Out of grammar scenarios now handled
  - User able to search on analysis sets or interactions. On interactions, users can also search using custom input data, interaction id or session id
  - Match results are not updated with Semantic Interpretation matches
- Update made to archiving. This was done to support data cleanup scripts for PostgreSQL and MongoDB
- MRCP
  - Detects end-of-speech when both speech & DTMF grammars are active at the same time
  - MRCP service doesn’t lockup whenever both the speechrecog and speechsynth resources are enabled in the same SIP INVITE SDP
  - MRCP server supports INVITEs with mime multipart content.
  - MRCP service correctly sets es_US for Spanish language SSML prompts, resulting in correct pronunciation of Spanish words
  - ASR SISR parse uses DTMF grammars only if set to grammars
  - ASR recognition using built-in DTMF grammar does not recognize speech
Container stack now supports Redis 7.0.0 (minimum requirement)

Installation notes

The following helm chart can be used

Helm Chart

Note that for MRCP there is no helm chart but a docker compose file. MRCP will run on its own Docker virtual machine which will integrate into the Kubernetes cluster.

Upgrade procedures

Upgrade or migration from previous versions is supported. Please contact LumenVox to discuss.

Updated API guide

APIs for all speech products available on version 4.4 can be obtained here: https://developer.lumenvox.com/4.4.0/

Information for voice biometric products relates to version 3.4.0-3.4.3

Model versions as part of the release

ASR - 4.1.0

TTS - 1.0 sample rate 22

VB - 2.1.15

VB incorporates Selene 2.4.3 which was integrated into the Container stack

Model version changes

None

Was this article helpful?