September 13, 2019
We propose a fully convolutional sequence-to-sequence encoder architecture with a simple and efficient decoder. Our model improves WER on LibriSpeech while being an order of magnitude more efficient than a strong RNN baseline. Key to our approach is a time-depth separable convolution block which dramatically reduces the number of parameters in the model while keeping the receptive field large. We also give a stable and efficient beam search inference procedure which allows us to effectively integrate a language model. Coupled with a convolutional language model, our time-depth separable convolution architecture improves by more than 22% relative WER over the best previously reported sequence-to-sequence results on the noisy LibriSpeech test set.
Publisher
Interspeech
November 04, 2026
Yosuke Higuchi, Tom Fizycki, Mahi Luthra, Charles-Éric Saint-James, Azeez Syed, Angel Villar Corrales, Mido Assran, Nicolas Ballas, Jiayi Shen, Dongyan Lin, Phillip Rust, Surya Parimi, Vanessa Stark, Alexandre Allauzen, Balázs Kegl, Juan Pino, Emmanuel Dupoux
November 04, 2026
October 19, 2026
Muse Glimmer team
October 19, 2026
October 14, 2026
Arturo Loaiza-Bonilla
October 14, 2026
October 14, 2026
Daniel Kim
October 14, 2026
