A Purely End-to-end System for Multi-speaker Speech Recognition
This addresses the problem of recognizing overlapping speech for applications like meeting transcription, but it is incremental as it builds on prior end-to-end methods.
The paper tackles multi-speaker speech recognition from mixed audio by proposing an end-to-end sequence-to-sequence framework that unifies source separation and recognition without needing extra training data, achieving an 83.1% relative improvement over a baseline without their objective function.
Recently, there has been growing interest in multi-speaker speech recognition, where the utterances of multiple speakers are recognized from their mixture. Promising techniques have been proposed for this task, but earlier works have required additional training data such as isolated source signals or senone alignments for effective learning. In this paper, we propose a new sequence-to-sequence framework to directly decode multiple label sequences from a single speech sequence by unifying source separation and speech recognition functions in an end-to-end manner. We further propose a new objective function to improve the contrast between the hidden vectors to avoid generating similar hypotheses. Experimental results show that the model is directly able to learn a mapping from a speech mixture to multiple label sequences, achieving 83.1 % relative improvement compared to a model trained without the proposed objective. Interestingly, the results are comparable to those produced by previous end-to-end works featuring explicit separation and recognition modules.