Streaming automatic speech recognition with the transformer model — mentioned by jonathanleroux

Tue, 14 Jan 2020 22:49:31 GMT

If I may insert a relevant plug: we (MERL) just put out a paper last week with SOTA 7.0 % WER on LibriSpeech test-other (vs wav2letter@anywhere's 7.5%) with 590 ms theoretical latency using joint CTC-Transformer with parallel time-delayed LSTM and triggered attention. Check it out: https://arxiv.org/abs/2001.02674

Paper and discussion history. A mention is not an endorsement.

Streaming automatic speech recognition with the transformer model · HackerPapers discussions

Streaming automatic speech recognition with the transformer model — mentioned by jonathanleroux