Conformer with dual-mode chunked attention for joint online and offline ASR

Weninger, Felix; Gaudesi, Marco; Haidar, Md Akmal; Ferri, Nicola; Andrés-Ferrer, Jesús; Zhan, Puming

doi:10.21437/interspeech.2022-733

Cited by 5 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar chunking in the decoder has been done in [14][15][16][17][18][19] and similar chunking in the encoder has been done in [7,[20][21][22][23][24][25][26][27][28][29]. There are also other approaches to make self-attention in the encoder streamable [9,30,31].…”

mentioning

confidence: 99%

Investigating Methods to Improve Language Model Integration for Attention-Based Encoder-Decoder ASR Models

Zeineldeen

Glushko²,

Michel

et al. 2021

Interspeech 2021

View full text Add to dashboard Cite

We study a streamable attention-based encoder-decoder model in which either the decoder, or both the encoder and decoder, operate on pre-defined, fixed-size windows called chunks. A special end-of-chunk (EOC) symbol advances from one chunk to the next chunk, effectively replacing the conventional end-of-sequence symbol. This modification, while minor, situates our model as equivalent to a transducer model that operates on chunks instead of frames, where EOC corresponds to the blank symbol. We further explore the remaining differences between a standard transducer and our model. Additionally, we examine relevant aspects such as long-form speech generalization, beam size, and length normalization. Through experiments on Librispeech and TED-LIUM-v2, and by concatenating consecutive sequences for long-form trials, we find that our streamable model maintains competitive performance compared to the non-streamable variant and generalizes very well to long-form speech.

show abstract