Maximum a posteriori Based Decoding for CTC Acoustic Models

By Naoyuki Kanda, Xugang Lu, Hisashi Kawai. 2016

44 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. Jinyu Li
2. Shinji Watanabe
3. Takaaki Hori
4. Bo Xu
5. Tomoki Hayashi
6. John R. Hershey
7. Dong Yu
8. Yu Zhang

In Signal Processing

1. Jinyu Li
2. Shinji Watanabe
3. Takaaki Hori
4. John R. Hershey
5. Bo Xu
6. Dong Yu
7. Tomoki Hayashi
8. Linhao Dong

Citations in the corpus

• Syllable-Based Sequence-to-Sequence Speech Recognition with the Transformer in Mandarin Chinese (2018, background): “The speech recognition problem can be defined as the problem of finding word sequence W that maximizes posterior probability Pr(W |X) given observation X , and can transform as follows [17].”
• Advances in Joint CTC-Attention Based End-to-End Speech Recognition with a Deep CNN Encoder and RNN-LM (2017, methodology): “recipe [27] and a system based on syllable-based CTC with MAP decoding [28].”
• Recent Advances in End-to-End Automatic Speech Recognition (2021, methodology): “As an improvement, a maximum a posteriori based decoding method [177, 178] was proposed for the integration of an external LM for CTC.”
• Hybrid CTC/Attention Architecture for End-to-End Speech Recognition (2017, methodology): “However, the theoretical justification and experimental effectiveness of this factor are shown in [27].”
• Joint CTC/attention decoding for end-to-end speech recognition (2017, methodology): “The state-of-the-art CERs of GMM discriminative training and DNN-sMBR/HMM systems are obtained from the Kaldi recipe (Moriya et al., 2015) and a system based on syllable-based CTC with MAP decoding (Kanda et al., 2016).”