# Speechmatics CTO - Next-Generation Speech Recognition

Page: https://stenobird.com/podcast/machine-learning-street-talk/speechmatics-cto-next-generation-speech-recognition
Text version: https://stenobird.com/podcast/machine-learning-street-talk/speechmatics-cto-next-generation-speech-recognition.md
Podcast: [Machine Learning Street Talk (MLST)](https://stenobird.com/podcast/machine-learning-street-talk)
Published: 2024-10-23T22:38:32+00:00
Episode link: https://podcasters.spotify.com/pod/show/machinelearningstreettalk/episodes/Speechmatics-CTO---Next-Generation-Speech-Recognition-e2q2g1a
Audio file: https://anchor.fm/s/1e4a0eac/podcast/play/93453802/https%3A%2F%2Fd3ctxlq1ktw2nl.cloudfront.net%2Fstaging%2F2024-9-23%2F28773177-f173-7635-f237-352753d4afbe.mp3
Processing state: processed
JSON: https://stenobird.com/v1/public/podcasts/machine-learning-street-talk/episodes/speechmatics-cto-next-generation-speech-recognition
Duration seconds: 6383

## Resource

Will Williams is CTO of Speechmatics in Cambridge. In this sponsored episode - he shares deep technical insights into modern speech recognition technology and system architecture. The episode covers several key technical areas: * Speechmatics' hybrid approach to ASR, which focusses on unsupervised learning methods, achieving comparable results with 100x less data than fully supervised approaches. Williams explains why this is more efficient and generalizable than end-to-end models like Whisper. * Their production architecture implementing multiple operating points for different latency-accuracy trade-offs, with careful latency padding (up to 1.8 seconds) to ensure consistent user experience. The system uses lattice-based decoding with language model integration for improved accuracy. * The challenges and solutions in real-time ASR, including their approach to diarization (speaker identification), handling cross-talk, and implicit source separation. Williams explains why these problems remain difficult even with modern deep learning approaches. * Their testing and deployment infrastructure, including the use of mirrored environments for catching edge cases in production, and their strategy of maintaining global models rather than allowing customer-specific fine-tuning. * Technical evolution in ASR, from early days of custom CUDA kernels and manual memory management to modern frameworks, with Williams offering interesting critiques of current PyTorch memory management approaches and arguing for more efficient direct memory allocation in production systems. Get coding with their API! This is their URL: https://www.speechmatics.com/ DO YOU WANT WORK ON ARC with the MindsAI team (current ARC winners)? MLST is sponsored by Tufa Labs: Focus: ARC, LLMs, test-time-compute, acti…

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/machine-learning-street-talk/episodes/speechmatics-cto-next-generation-speech-recognition/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/machine-learning-street-talk/speechmatics-cto-next-generation-speech-recognition.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.