Neural Text Normalization with Subword Units
Text normalization (TN) is an important step in conversational systems. It converts written text to its spoken form to facilitate speech recognition, natural language understanding and text-to-speech synthesis. Finite state transducers (FSTs) are commonly used to build grammars that handle text normalization. However, translating linguistic knowledge into grammars requires extensive effort. In this paper, we frame TN as a machine translation task and tackle it with sequence-to-sequence (seq2seq) models. Previous research focuses on normalizing a word (or phrase) with the help of limited word-level context, while our approach directly normalizes full sentences. We find subword models with additional linguistic features yield the best performance (with a word error rate of 0.17{\%}).
Code (0)
등록된 구현이 없습니다.
Tasks
Machine TranslationNatural Language Understandingspeech-recognitionSpeech RecognitionSpeech SynthesisText Normalizationtext-to-speechText to SpeechText-To-Speech SynthesisTranslationSimilar Papers 제목 키워드 기반
Hybrid CTC-Attention based End-to-End Speech Recognition using Subword Units
In this paper, we present an end-to-end automatic speech recognition system, which successfully employs subword units in a hybrid CTC-Attention based system. The subword units are obtained by the byte-pair encoding (BPE)…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Language ModelingLanguage Modelling+2Neural Named Entity Recognition from Subword Units
Named entity recognition (NER) is a vital task in spoken language understanding, which aims to identify mentions of named entities in text e.g., from transcribed speech. Existing neural models for NER rely mostly on dedi…
named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NER+1Acoustic Data-Driven Subword Modeling for End-to-End Speech Recognition
Subword units are commonly used for end-to-end automatic speech recognition (ASR), while a fully acoustic-oriented subword modeling approach is somewhat missing. We propose an acoustic data-driven subword modeling (ADSM)…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Segmentationspeech-recognition+2Improving Neural Machine Translation by Incorporating Hierarchical Subword Features
This paper focuses on subword-based Neural Machine Translation (NMT). We hypothesize that in the NMT model, the appropriate subword units for the following three modules (layers) can differ: (1) the encoder embedding lay…
DecoderMachine TranslationNMTTranslationSubword and Crossword Units for CTC Acoustic Models
This paper proposes a novel approach to create an unit set for CTC based speech recognition systems. By using Byte Pair Encoding we learn an unit set of an arbitrary size on a given training text. In contrast to using ch…
Language ModelingLanguage Modellingspeech-recognitionSpeech Recognition