[PDF][PDF] Recent advances in end-to-end automatic speech recognition
J Li - APSIPA Transactions on Signal and Information …, 2022 - nowpublishers.com
Recently, the speech community is seeing a significant trend of moving from deep neural
network based hybrid modeling to end-to-end (E2E) modeling for automatic speech …
network based hybrid modeling to end-to-end (E2E) modeling for automatic speech …
VarArray meets t-SOT: Advancing the state of the art of streaming distant conversational speech recognition
This paper presents a novel streaming automatic speech recognition (ASR) framework for
multi-talker overlapping speech captured by a distant microphone array with an arbitrary …
multi-talker overlapping speech captured by a distant microphone array with an arbitrary …
Serialized output training for end-to-end overlapped speech recognition
This paper proposes serialized output training (SOT), a novel framework for multi-speaker
overlapped speech recognition based on an attention-based encoder-decoder approach …
overlapped speech recognition based on an attention-based encoder-decoder approach …
Streaming multi-talker ASR with token-level serialized output training
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 …
streaming multi-talker automatic speech recognition (ASR). Unlike existing streaming multi …
A conformer-based asr frontend for joint acoustic echo cancellation, speech enhancement and speech separation
T O'Malley, A Narayanan, Q Wang… - 2021 IEEE Automatic …, 2021 - ieeexplore.ieee.org
We present a frontend for improving robustness of automatic speech recognition (ASR), that
jointly implements three modules within a single model: acoustic echo cancellation, speech …
jointly implements three modules within a single model: acoustic echo cancellation, speech …
Large-scale pre-training of end-to-end multi-talker ASR for meeting transcription with single distant microphone
Transcribing meetings containing overlapped speech with only a single distant microphone
(SDM) has been one of the most challenging problems for automatic speech recognition …
(SDM) has been one of the most challenging problems for automatic speech recognition …
Streaming end-to-end multi-talker speech recognition
End-to-end multi-talker speech recognition is an emerging research trend in the speech
community due to its vast potential in applications such as conversation and meeting …
community due to its vast potential in applications such as conversation and meeting …
Streaming multi-speaker ASR with RNN-T
Recent research shows end-to-end ASR systems can recognize overlapped speech from
multiple speakers. However, all published works have assumed no latency constraints …
multiple speakers. However, all published works have assumed no latency constraints …
Multi-turn RNN-T for streaming recognition of multi-party speech
Automatic speech recognition (ASR) of single channel far-field recordings with an unknown
number of speakers is traditionally tackled by cascaded modules. Recent research shows …
number of speakers is traditionally tackled by cascaded modules. Recent research shows …
A sidecar separator can convert a single-talker speech recognition system to a multi-talker one
Although automatic speech recognition (ASR) can perform well in common non-overlapping
environments, sustaining performance in multi-talker overlapping speech recognition …
environments, sustaining performance in multi-talker overlapping speech recognition …