Non-autoregressive text to speech (TTS) models such as FastSpeech can synthesize speech significantly faster than previous autoregressive models with comparable quality. The training of FastSpeech model relies on an autoregressive teacher model for duration prediction (to provide more information as input) and knowledge distillation (to simplify the data distribution in output), which can ease the one-to-many mapping problem (i.e., multiple speech variations correspond to the same text) in TTS. However, FastSpeech has several disadvantages: 1) the teacher-student distillation pipeline is complicated and time-consuming, 2) the duration extracted from the teacher model is not accurate enough, and the target mel-spectrograms distilled from teacher model suffer from information loss due to data simplification, both of which limit the voice quality. In this paper, we propose FastSpeech 2, which addresses the issues in FastSpeech and better solves the one-to-many mapping problem in TTS by 1) directly training the model with ground-truth target instead of the simplified output from teacher, and 2) introducing more variation information of speech (e.g., pitch, energy and more accurate duration) as conditional inputs. Specifically, we extract duration, pitch and energy from speech waveform and directly take them as conditional inputs in training and use predicted values in inference. We further design FastSpeech 2s, which is the first attempt to directly generate speech waveform from text in parallel, enjoying the benefit of fully end-to-end inference. Experimental results show that 1) FastSpeech 2 achieves a 3x training speed-up over FastSpeech, and FastSpeech 2s enjoys even faster inference speed; 2) FastSpeech 2 and 2s outperform FastSpeech in voice quality, and FastSpeech 2 can even surpass autoregressive models. Audio samples are available at this https URL.

FastSpeech 2: Fast and High-Quality End-to-End Text to Speech

Custom voice, a specific text to speech (TTS) service in commercial speech platforms, aims to adapt a source TTS model to synthesize personal voice for a target speaker using few speech from her/him. Custom voice presents two unique challenges for TTS adaptation: 1) to support diverse customers, the adaptation model needs to handle diverse acoustic conditions which could be very different from source speech data, and 2) to support a large number of customers, the adaptation parameters need to be small enough for each target speaker to reduce memory usage while maintaining high voice quality. In this work, we propose AdaSpeech, an adaptive TTS system for high-quality and efficient customization of new voices. We design several techniques in AdaSpeech to address the two challenges in custom voice: 1) To handle different acoustic conditions, we model the acoustic information in both utterance and phoneme level. Specifically, we use one acoustic encoder to extract an utterance-level vector and another one to extract a sequence of phoneme-level vectors from the target speech during pre-training and fine-tuning; in inference, we extract the utterance-level vector from a reference speech and use an acoustic predictor to predict the phoneme-level vectors. 2) To better trade off the adaptation parameters and voice quality, we introduce conditional layer normalization in the mel-spectrogram decoder of AdaSpeech, and fine-tune this part in addition to speaker embedding for adaptation. We pre-train the source TTS model on LibriTTS datasets and fine-tune it on VCTK and LJSpeech datasets (with different acoustic conditions from LibriTTS) with few adaptation data, e.g., 20 sentences, about 1 minute speech. Experiment results show that AdaSpeech achieves much better adaptation quality than baseline methods, with only about 5K specific parameters for each speaker, which demonstrates its effectiveness for custom voice. The audio samples are available at https://speechresearch.github.io/adaspeech/.

/pdf/adaspeech-adaptive-text-to-speech-for-custom-voice-4xq89t7o4e.pdf

AdaSpeech: Adaptive Text to Speech for Custom Voice

Text to speech (TTS), or speech synthesis, which aims to synthesize intelligible and natural speech given text, is a hot research topic in speech, language, and machine learning communities and has broad applications in the industry. As the development of deep learning and artificial intelligence, neural network-based TTS has significantly improved the quality of synthesized speech in recent years. In this paper, we conduct a comprehensive survey on neural TTS, aiming to provide a good understanding of current research and future trends. We focus on the key components in neural TTS, including text analysis, acoustic models and vocoders, and several advanced topics, including fast TTS, low-resource TTS, robust TTS, expressive TTS, and adaptive TTS, etc. We further summarize resources related to TTS (e.g., datasets, opensource implementations) and discuss future research directions. This survey can serve both academic researchers and industry practitioners working on TTS.

A Survey on Neural Speech Synthesis.

The visually impaired suffer greatly while moving from one place to another. They face challenges in going outdoors and in protecting themselves from moving and stationary objects, and they also lack confidence due to restricted mobility. Due to the recent rapid rise in the number of visually impaired persons, the development of assistive devices has emerged as a significant research field. This review study introduces several techniques to help the visually impaired with their mobility and presents the state-of-the-art of recent assistive technologies that facilitate their everyday life. It also analyses comprehensive multiple mobility assistive technologies for indoor and outdoor environments and describes the different location and feedback methods for the visually impaired using assistive tools based on recent technologies. The navigation tools used for the visually impaired are discussed in detail in subsequent sections. Finally, a detailed analysis of various methods is also carried out, with future recommendations.

/pdf/review-of-navigation-assistive-tools-and-technologies-for-3a3v166u.pdf

Review of Navigation Assistive Tools and Technologies for the Visually Impaired

Transformer-based Deep Neural Network architectures have gained tremendous interest due to their effectiveness in various applications across Natural Language Processing (NLP) and Computer Vision (CV) domains. These models are the de facto choice in several language tasks, such as Sentiment Analysis and Text Summarization, replacing Long Short Term Memory (LSTM) model. Vision Transformers (ViTs) have shown better model performance than traditional Convolutional Neural Networks (CNNs) in vision applications while requiring significantly fewer parameters and training time. The design pipeline of a neural architecture for a given task and dataset is extremely challenging as it requires expertise in several interdisciplinary areas such as signal processing, image processing, optimization and allied fields. Neural Architecture Search (NAS) is a promising technique to automate the architectural design process of a Neural Network in a data-driven way using Machine Learning (ML) methods. The search method explores several architectures without requiring significant human effort, and the searched models outperform the manually built networks. In this paper, we review Neural Architecture Search techniques, targeting the Transformer model and its family of architectures such as Bidirectional Encoder Representations from Transformers (BERT) and Vision Transformers. We provide an in-depth literature review of approximately 50 state-of-the-art Neural Architecture Search methods and explore future directions in this fast-evolving class of problems.

https://ieeexplore.ieee.org/ielx7/6287639/6514899/09913476.pdf

Neural Architecture Search for Transformers: A Survey

Text to speech (TTS) has been broadly used to synthesize natural and intelligible speech in different scenarios. Deploying TTS in various end devices such as mobile phones or embedded devices requires extremely small memory usage and inference latency. While non-autoregressive TTS models such as FastSpeech have achieved significantly faster inference speed than autoregressive models, their model size and inference latency are still large for the deployment in resource constrained devices. In this paper, we propose LightSpeech, which leverages neural architecture search (NAS) to automatically design more lightweight and efficient models based on FastSpeech. We first profile the components of current Fast-Speech model and carefully design a novel search space containing various lightweight and potentially effective architectures. Then NAS is utilized to automatically discover well performing architectures within the search space. Experiments show that the model discovered by our method achieves 15x model compression ratio and 6.5x inference speedup on CPU with on par voice quality. Audio demos are provided at https://speechresearch.github.io/lightspeech.

Lightspeech: Lightweight and Fast Text to Speech with Neural Architecture Search

Text to speech (TTS) has been broadly used to synthesize natural and intelligible speech in different scenarios. Deploying TTS in various end devices such as mobile phones or embedded devices requires extremely small memory usage and inference latency. While non-autoregressive TTS models such as FastSpeech have achieved significantly faster inference speed than autoregressive models, their model size and inference latency are still large for the deployment in resource constrained devices. In this paper, we propose LightSpeech, which leverages neural architecture search~(NAS) to automatically design more lightweight and efficient models based on FastSpeech. We first profile the components of current FastSpeech model and carefully design a novel search space containing various lightweight and potentially effective architectures. Then NAS is utilized to automatically discover well performing architectures within the search space. Experiments show that the model discovered by our method achieves 15x model compression ratio and 6.5x inference speedup on CPU with on par voice quality. Audio demos are provided at this https URL.

LightSpeech: Lightweight and Fast Text to Speech with Neural Architecture Search

This paper describes the Microsoft end-to-end neural text to speech (TTS) system: DelightfulTTS for Blizzard Challenge 2021. The goal of this challenge is to synthesize natural and high-quality speech from text, and we approach this goal in two perspectives: The first is to directly model and generate waveform in 48 kHz sampling rate, which brings higher perception quality than previous systems with 16 kHz or 24 kHz sampling rate; The second is to model the variation information in speech through a systematic design, which improves the prosody and naturalness. Specifically, for 48 kHz modeling, we predict 16 kHz mel-spectrogram in acoustic model, and propose a vocoder called HiFiNet to directly generate 48 kHz waveform from predicted 16 kHz mel-spectrogram, which can better trade off training efficiency, modelling stability and voice quality. We model variation information systematically from both explicit (speaker ID, language ID, pitch and duration) and implicit (utterance-level and phoneme-level prosody) perspectives: 1) For speaker and language ID, we use lookup embedding in training and inference; 2) For pitch and duration, we extract the values from paired text-speech data in training and use two predictors to predict the values in inference; 3) For utterance-level and phoneme-level prosody, we use two reference encoders to extract the values in training, and use two separate predictors to predict the values in inference. Additionally, we introduce an improved Conformer block to better model the local and global dependency in acoustic model. For task SH1, DelightfulTTS achieves 4.17 mean score in MOS test and 4.35 in SMOS test, which indicates the effectiveness of our proposed system

DelightfulTTS: The Microsoft Speech Synthesis System for Blizzard Challenge 2021

This paper describes the Microsoft Text-to-Speech (TTS) system: LeanSpeech for LIMMITS (Lightweight, Multi-speaker, Multi-lingual Indic TTS) Challenge 2023 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> , which is part of ICASSP2023 to encourage the advance of TTS in Indian Languages. We propose a lightweight encoder-decoder acoustic model composed of 1-D convolution and LSTM blocks, which is trained with knowledge distillation from a multi-speaker multi-lingual teacher model, DelightfulTTS [1]. The speech corpus is reprocessed and used in both AM training and vocoder fine-tuning. In Track-2 of the challenge, our system achieves MOS 4.56 and SMOS 3.98, which indicates the efficiency of the proposed model and training strategy. 

Jinzhu Li

Papers

Lightspeech: Lightweight and Fast Text to Speech with Neural Architecture Search

LightSpeech: Lightweight and Fast Text to Speech with Neural Architecture Search

DelightfulTTS: The Microsoft Speech Synthesis System for Blizzard Challenge 2021

LeanSpeech: The Microsoft Lightweight Speech Synthesis System for Limmits Challenge 2023