Zipformer: A faster and better encoder for automatic speech recognition.
Zengwei YaoLiyong GuoXiaoyu YangWei KangFangjun KuangYifan YangZengrui JinLong LinDaniel PoveyPublished in: ICLR (2024)
Keyphrases
- automatic speech recognition
- speech recognition
- speech signal
- hidden markov models
- word error rate
- conversational speech
- acoustic features
- word recognition
- broadcast news
- speech retrieval
- recognition errors
- bit rate
- discriminative training
- spoken words
- noisy environments
- image processing
- speech corpus
- image coding
- spontaneous speech
- multi modal
- computer vision
- compound words
- machine learning
- neural network