Improving Speech Recognition for African American English With Audio Classification.
Shefali GargZhouyuan HuoKhe Chai SimSuzan SchwartzMason ChuaAlëna AksënovaTsendsuren MunkhdalaiLevi KingDarryl WrightZion MengeshaDongseong HwangTara N. SainathFrançoise BeaufaysPedro Moreno MengibarPublished in: CoRR (2023)
Keyphrases
- speech recognition
- speech recognition technology
- pattern recognition
- speaker identification
- speech processing
- speech synthesis
- automatic speech recognition
- broadcast news
- audio visual speech recognition
- hidden markov models
- speech recognizer
- text to speech
- speech signal
- language model
- classification accuracy
- machine learning
- speech retrieval
- cepstral coefficients
- mel frequency cepstral coefficients
- feature set
- significantly higher
- support vector machine
- speaker independent
- students with learning disabilities
- signal processing
- african american
- isolated word
- multimedia
- speech recognition systems
- data mining
- neural network
- multi stream
- feature vectors
- english language