Syllable-based acoustic modeling with CTC-SMBR-LSTM

By Zhongdi Qu, Parisa Haghani, Eugene Weinstein, Pedro J. Moreno Mengibar. 2017

31 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Bo Xu
2. Linhao Dong
3. Jinyu Li
4. Shuang Xu
5. Shiyu Zhou
6. Dong Yu
7. Dan Su
8. Zhao You

In Signal Processing

1. Bo Xu
2. Jinyu Li
3. Linhao Dong
4. Shuang Xu
5. Shiyu Zhou
6. Dan Su
7. Zhao You
8. Dong Yu

Citations in the corpus

• Syllable-Based Sequence-to-Sequence Speech Recognition with the Transformer in Mandarin Chinese (2018, methodology): “[13] explored the CTC-SMBR-LSTM using syllables as outputs and verified that syllable based CTC model can perform better than CIphoneme based CTC model on Mandarin Chinese ASR tasks.”
• SpeechMoE: Scaling to Large Acoustic Models with Dynamic Routing Mixture of Experts (2021, methodology): “We use the context-independent-syllablebased acoustic modeling method [24] for CTC learning.”
• Speechmoe2: Mixture-of-Experts Model with Improved Routing (2021, methodology): “We use the context-independent-syllable-based acoustic modeling method [15] for CTC learning.”