Transformer-Based Acoustic Modeling for Hybrid Speech Recognition.
Yongqiang WangAbdelrahman MohamedDuc LeChunxi LiuAlex XiaoJay MahadeokarHongzhao HuangAndros TjandraXiaohui ZhangFrank ZhangChristian FuegenGeoffrey ZweigMichael L. SeltzerPublished in: ICASSP (2020)
Keyphrases
- speech recognition
- speech recognition systems
- speaker independent
- speech recognizers
- hidden markov models
- acoustic models
- speech processing
- speech synthesis
- speech recognizer
- noisy environments
- language model
- automatic speech recognition
- speech understanding
- noisy speech
- speaker identification
- speech signal
- speech recognition technology
- speaker dependent
- keyword spotting
- pattern recognition
- image processing
- cepstral coefficients
- speaker adaptation
- multi modal
- feature extraction
- computer vision
- audio visual speech recognition