The reviewed record of science sign in
Pith

arxiv: 2310.01688 · v1 · pith:H6KP3FJ6 · submitted 2023-10-02 · eess.AS · cs.CL· cs.SD

One model to rule them all ? Towards End-to-End Joint Speaker Diarization and Speech Recognition

Reviewed by Pithpith:H6KP3FJ6open to challenge →

classification eess.AS cs.CLcs.SD
keywords speakerspeechdiarizationmodelrecognitionslidardastdiarization-augmented
0
0 comments X
read the original abstract

This paper presents a novel framework for joint speaker diarization (SD) and automatic speech recognition (ASR), named SLIDAR (sliding-window diarization-augmented recognition). SLIDAR can process arbitrary length inputs and can handle any number of speakers, effectively solving ``who spoke what, when'' concurrently. SLIDAR leverages a sliding window approach and consists of an end-to-end diarization-augmented speech transcription (E2E DAST) model which provides, locally, for each window: transcripts, diarization and speaker embeddings. The E2E DAST model is based on an encoder-decoder architecture and leverages recent techniques such as serialized output training and ``Whisper-style" prompting. The local outputs are then combined to get the final SD+ASR result by clustering the speaker embeddings to get global speaker identities. Experiments performed on monaural recordings from the AMI corpus confirm the effectiveness of the method in both close-talk and far-field speech scenarios.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.