End-to-End Multi-Speaker Speech Recognition using Speaker Embeddings and Transfer Learning
This addresses the problem of transcribing overlapping speech in ASR systems, which is incremental as it builds on existing end-to-end methods with specific conditioning and transfer learning techniques.
The paper tackles automatic speech recognition for overlapped speech by training an end-to-end system conditioned on speaker embeddings and enhanced with transfer learning from clean speech, achieving significant performance improvements on overlapped speech datasets.
This paper presents our latest investigation on end-to-end automatic speech recognition (ASR) for overlapped speech. We propose to train an end-to-end system conditioned on speaker embeddings and further improved by transfer learning from clean speech. This proposed framework does not require any parallel non-overlapped speech materials and is independent of the number of speakers. Our experimental results on overlapped speech datasets show that joint conditioning on speaker embeddings and transfer learning significantly improves the ASR performance.