Predicting Prosodic Prominence from Text with Pre-trained Contextualized Word Representations
In this paper we introduce a new natural language processing dataset and benchmark for predicting prosodic prominence from written text. To our knowledge this will be the largest publicly available dataset with prosodic labels. We describe the dataset construction and the resulting benchmark dataset in detail and train a number of different models ranging from feature-based classifiers to neural network systems for the prediction of discretized prosodic prominence. We show that pre-trained contextualized word representations from BERT outperform the other models even with less than 10% of the training data. Finally we discuss the dataset in light of the results and point to future research and plans for further improving both the dataset and methods of predicting prosodic prominence from text. The dataset and the code for the models are publicly available.
Code (1)
Tasks
Prosody PredictionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Prominence-aware automatic speech recognition for conversational speech
This paper investigates prominence-aware automatic speech recognition (ASR) by combining prominence detection and speech recognition for conversational Austrian German. First, prominence detectors were developed by fine-…
Speech RecognitionBERT, can HE predict contrastive focus? Predicting and controlling prominence in neural TTS using a language model
Several recent studies have tested the use of transformer language model representations to infer prosodic features for text-to-speech synthesis (TTS). While these studies have explored prosody in general, in this work, …
Language ModelingLanguage ModellingSpeech Synthesistext-to-speech+2Prosody leaks into the memories of words
The average predictability (aka informativity) of a word in context has been shown to condition word duration (Seyfarth, 2014). All else being equal, words that tend to occur in more predictable environments are shorter …
Prosodic Prominence and Boundaries in Sequence-to-Sequence Speech Synthesis
Recent advances in deep learning methods have elevated synthetic speech quality to human level, and the field is now moving towards addressing prosodic variation in synthetic speech.Despite successes in this effort, the …
SentenceSpeech SynthesisHierarchical Representation of Prosody for Statistical Speech Synthesis
Prominences and boundaries are the essential constituents of prosodic structure in speech. They provide for means to chunk the speech stream into linguistically relevant units by providing them with relative saliences an…
Speech Synthesistext-to-speechText to SpeechText-To-Speech Synthesis