Self-supervised learning (SSL) achieves great success in speech recognition, while limited
exploration has been attempted for other speech processing tasks. As speech signal …

This paper proposes a token-level serialized output training (t-SOT), a novel framework for
streaming multi-talker automatic speech recognition (ASR). Unlike existing streaming multi …

Deep learning based wideband (16kHz) acoustic echo cancellation (AEC) approaches have
surpassed traditional methods. This work proposes a deep hierarchical fusion (DHF) …

Self-supervised learning (SSL) methods such as WavLM have shown promising speech
separation (SS) results in small-scale simulation-based experiments. In this work, we extend …

Serialized Output Training (SOT) has showcased state-of-the-art performance in multi-talker
speech recognition by sequentially decoding the speech of individual speakers. To address …

The Streaming Unmixing and Recognition Transducer (SURT) has recently become a
popular framework for continuous, streaming, multi-talker speech recognition (ASR). With …

Lyrics transcription of polyphonic music is challenging as the background music affects lyrics
intelligibility. Typically, lyrics transcription can be performed by a two-step pipeline, ie a …

Deep learning-based wideband (16kHz) speech enhancement approaches have surpassed
traditional methods. This work further extends the existing wideband systems to enable full …

This letter presents a new target speech recognition problem, where the target speech is
defined by a keyword. For instance, when a person speaks “Hey Google” or “Help Me”, we …

Existing multi-channel continuous speech separation (CSS) models are heavily dependent
on supervised data-either simulated data which causes data mismatch between the training …