Multimodal Speech Recognition for Language-Guided Embodied Agents.
Allen ChangXiaoyuan ZhuAarav MongaSeoho AhnTejas SrinivasanJesse ThomasonPublished in: INTERSPEECH (2023)
Keyphrases
- speech recognition
- embodied agents
- isolated word
- hidden markov models
- automatic speech recognition
- pattern recognition
- language model
- speech synthesis
- speech processing
- speech signal
- speech recognition systems
- speech recognizer
- language learning
- speaker identification
- virtual humans
- multi modal
- noisy environments
- natural language
- linguistic knowledge
- english text
- language processing
- audio visual
- virtual environment
- speech recognition technology