Related papers: Speech BERT Embedding For Improving Prosody in Neu…

We propose a novel phrase break prediction method that combines implicit features extracted from a pre-trained large language model, a.k.a BERT, and explicit features extracted from BiLSTM with linguistic features. In conventional BiLSTM…

Current synthetic speech detection (SSD) methods perform well on certain datasets but still face issues of robustness and interpretability. A possible reason is that these methods do not analyze the deficiencies of synthetic speech. In this…

Neural machine translation models are often biased toward the limited translation references seen during training. To amend this form of overfitting, in this paper we propose fine-tuning the models with a novel training objective based on…

We propose a novel text-to-speech (TTS) framework centered around a neural transducer. Our approach divides the whole TTS pipeline into semantic-level sequence-to-sequence (seq2seq) modeling and fine-grained acoustic modeling stages,…

Transformer architectures show significant promise for natural language processing. Given that a single pretrained model can be fine-tuned to perform well on many different tasks, these networks appear to extract generally useful linguistic…

We propose a novel causal prosody mediation framework for expressive text-to-speech (TTS) synthesis. Our approach augments the FastSpeech2 architecture with explicit emotion conditioning and introduces counterfactual training objectives to…

Contextualized word embeddings derived from pre-trained language models (LMs) show significant improvements on downstream NLP tasks. Pre-training on domain-specific corpora, such as biomedical articles, further improves their performance.…

While modern TTS technologies have made significant advancements in audio quality, there is still a lack of behavior naturalness compared to conversing with people. We propose a style-embedded TTS system that generates styled responses…

This paper presents BERT-CTC, a novel formulation of end-to-end speech recognition that adapts BERT for connectionist temporal classification (CTC). Our formulation relaxes the conditional independence assumptions used in conventional CTC…

For self-supervised speech processing, it is crucial to use pretrained models as speech representation extractors. In recent works, increasing the size of the model has been utilized in acoustic model training in order to achieve better…

Models based on the transformer architecture, such as BERT, have marked a crucial step forward in the field of Natural Language Processing. Importantly, they allow the creation of word embeddings that capture important semantic information…

The mapping of text to speech (TTS) is non-deterministic, letters may be pronounced differently based on context, or phonemes can vary depending on various physiological and stylistic factors like gender, age, accent, emotions, etc. Neural…

The latest work on language representations carefully integrates contextualized features into language model training, which enables a series of success especially in various machine reading comprehension and natural language inference…

Sentence embeddings encode sentences in fixed dense vectors and have played an important role in various NLP tasks and systems. Methods for building sentence embeddings include unsupervised learning such as Quick-Thoughts and supervised…

We propose a novel Multi-Scale Spectrogram (MSS) modelling approach to synthesise speech with an improved coarse and fine-grained prosody. We present a generic multi-scale spectrogram prediction mechanism where the system first predicts…

In this paper, we propose a feature reinforcement method under the sequence-to-sequence neural text-to-speech (TTS) synthesis framework. The proposed method utilizes the multiple input encoder to take three levels of text information, i.e.,…

Previous work has established that a person's demographics and speech style affect how well speech processing models perform for them. But where does this bias come from? In this work, we present the Speech Embedding Association Test…

A crucial step in processing speech audio data for information extraction, topic detection, or browsing/playback is to segment the input into sentence and topic units. Speech segmentation is challenging, since the cues typically present for…

Neural Machine Translation (NMT) is the task of translating a text from one language to another with the use of a trained neural network. Several existing works aim at incorporating external information into NMT models to improve or control…

We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models, BERT is designed to pre-train deep bidirectional…