HK-LegiCoST: Leveraging Non-Verbatim Transcripts for Speech Translation.
Cihan XiaoHenry Li XinyuanJinyi YangDongji GaoMatthew WiesnerKevin DuhSanjeev KhudanpurPublished in: CoRR (2023)
Keyphrases
- automatic speech recognition
- broadcast news
- spoken documents
- language resources
- speech recognition
- spontaneous speech
- speech signal
- speech recognizers
- out of vocabulary
- speech transcripts
- spoken document retrieval
- content analysis
- machine translation
- speech recognizer
- audio visual
- speech synthesis
- recognition engine
- hidden markov models
- spoken term detection
- dialogue system
- cross language information retrieval
- multi modal
- speaker identification
- language acquisition
- cross language
- automatically generated
- language model
- pattern recognition
- spoken language
- emotion recognition
- human generated
- cross lingual
- automatic speech recognition systems