Pith. sign in

REVIEW

Towards Effective and Compact Contextual Representation for Conformer Transducer Speech Recognition Systems

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2306.13307 v2 pith:TVRX4AHX submitted 2023-06-23 eess.AS cs.CL

classification eess.AScs.CL
keywords utterancecompactcontextcontextscontextualcrosshistorylevel
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Current ASR systems are mainly trained and evaluated at the utterance level. Long range cross utterance context can be incorporated. A key task is to derive a suitable compact representation of the most relevant history contexts. In contrast to previous researches based on either LSTM-RNN encoded histories that attenuate the information from longer range contexts, or frame level concatenation of transformer context embeddings, in this paper compact low-dimensional cross utterance contextual features are learned in the Conformer-Transducer Encoder using specially designed attention pooling layers that are applied over efficiently cached preceding utterances history vectors. Experiments on the 1000-hr Gigaspeech corpus demonstrate that the proposed contextualized streaming Conformer-Transducers outperform the baseline using utterance internal context only with statistically significant WER reductions of 0.7% to 0.5% absolute (4.3% to 3.1% relative) on the dev and test data.

Discussion (0). Sign in to comment.

Pith tools