Analyzing the Impact of HF-Specific Signal Degradation on Automatic Speech Recognition.
Fabian FritzAlessia Cornaggia-UrrigshardtLukas HennekeFrank KurthKevin WilkinghoffPublished in: ICMCIS (2024)
Keyphrases
- automatic speech recognition
- high frequency
- speech recognition
- noisy environments
- speech signal
- conversational speech
- speech segments
- low frequency
- spoken words
- machine learning
- speech corpus
- acoustic features
- broadcast news
- word error rate
- frequency domain
- hidden markov models
- speech synthesis
- multi modal
- information retrieval