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 https://speechresearch.github.io/lightspeech.
We propose a lightweight end-to-end text-to-speech model using multi-band generation and inverse short-time Fourier transform. Our model is based on VITS, a high-quality end-to-end text-to-speech model, but adopts two changes for more efficient inference: 1) the most computationally expensive component is partially replaced with a simple inverse short-time Fourier transform, and 2) multi-band generation, with fixed or trainable synthesis filters, is used to generate waveforms. Unlike conventional lightweight models, which employ optimization or knowledge distillation separately to train two ca…
Automatic speech synthesis is a challenging task that is becoming increasingly important as edge devices begin to interact with users through speech. Typical text-to-speech pipelines include a vocoder, which translates intermediate audio representations into an audio waveform. Most existing vocoders are difficult to parallelize since each generated sample is conditioned on previous samples. WaveGlow is a flow-based feed-forward alternative to these auto-regressive models (Prenger et al., 2019). However, while WaveGlow can be easily parallelized, the model is too expensive for real-time speech …
Indiana University（印第安纳大学）；Electronics and Telecommunications Research Institute（电子与电信研究院）
Speech codecs learn compact representations of speech signals to facilitate data transmission. Many recent deep neural network (DNN) based end-to-end speech codecs achieve low bitrates and high perceptual quality at the cost of model complexity. We propose a cross-module residual learning (CMRL) pipeline as a module carrier with each module reconstructing the residual from its preceding modules. CMRL differs from other DNN-based speech codecs, in that rather than modeling speech compression problem in a single large neural network, it optimizes a series of less-complicated modules in a two-pha…
NTT Communication Science Laboratories, NTT Corporation（NTT 公司 NTT 通信科学实验室）
In speech synthesis, a generative adversarial network (GAN), training a generator (speech synthesizer) and a discriminator in a min-max game, is widely used to improve speech quality. An ensemble of discriminators is commonly used in recent neural vocoders (e.g., HiFi-GAN) and end-to-end text-to-speech (TTS) systems (e.g., VITS) to scrutinize waveforms from multiple perspectives. Such discriminators allow synthesized speech to adequately approach real speech; however, they require an increase in the model size and computation time according to the increase in the number of discriminators. Alte…
We introduce VANI, a very lightweight multi-lingual accent controllable speech synthesis system. Our model builds upon disentanglement strategies proposed in RADMMM and supports explicit control of accent, language, speaker and fine-grained $F_0$ and energy features for speech synthesis. We utilize the Indic languages dataset, released for LIMMITS 2023 as part of ICASSP Signal Processing Grand Challenge, to synthesize speech in 3 different languages. Our model supports transferring the language of a speaker while retaining their voice and the native accent of the target language. We utilize th…
FLY-TTS: Fast, Lightweight and High-Quality End-to-End Text-to-Speech Synthesis
College of Information Science and Electronic Engineering, Zhejiang University（浙江大学信息科学与工程学院）；College of Information Science（信息学院）；Electronic Engineering, Zhejiang University（浙江大学电子工程学院）
Highly performing deep neural networks come at the cost of computational complexity that limits their practicality for deployment on portable devices. We propose the low-rank transformer (LRT), a memory-efficient and fast neural architecture that significantly reduces the parameters and boosts the speed of training and inference for end-to-end speech recognition. Our approach reduces the number of parameters of the network by more than 50% and speeds up the inference time by around 1.35x compared to the baseline transformer model. The experiments show that our LRT model generalizes better and …
Several solutions for lightweight TTS have shown promising results. Still, they either rely on a hand-crafted design that reaches non-optimum size or use a neural architecture search but often suffer training costs. We present Nix-TTS, a lightweight TTS achieved via knowledge distillation to a high-quality yet large-sized, non-autoregressive, and end-to-end (vocoder-free) TTS teacher model. Specifically, we offer module-wise distillation, enabling flexible and independent distillation to the encoder and decoder module. The resulting Nix-TTS inherited the advantageous properties of being non-au…
In recent years, neural vocoders have surpassed classical speech generation approaches in naturalness and perceptual quality of the synthesized speech. Computationally heavy models like WaveNet and WaveGlow achieve best results, while lightweight GAN models, e.g. MelGAN and Parallel WaveGAN, remain inferior in terms of perceptual quality. We therefore propose StyleMelGAN, a lightweight neural vocoder allowing synthesis of high-fidelity speech with low computational complexity. StyleMelGAN employs temporal adaptive normalization to style a low-dimensional noise vector with the acoustic features…
We present a lightweight adaptable neural TTS system with high quality output. The system is composed of three separate neural network blocks: prosody prediction, acoustic feature prediction and Linear Prediction Coding Net as a neural vocoder. This system can synthesize speech with close to natural quality while running 3 times faster than real-time on a standard CPU. The modular setup of the system allows for simple adaptation to new voices with a small amount of data. We first demonstrate the ability of the system to produce high quality speech when trained on large, high quality datasets. …
National Taiwan University（国立台湾大学）；Intelligo Technology Inc.（Intelligo科技公司）
Personalized TTS is an exciting and highly desired application that allows users to train their TTS voice using only a few recordings. However, TTS training typically requires many hours of recording and a large model, making it unsuitable for deployment on mobile devices. To overcome this limitation, related works typically require fine-tuning a pre-trained TTS model to preserve its ability to generate high-quality audio samples while adapting to the target speaker's voice. This process is commonly referred to as ``voice cloning.'' Although related works have achieved significant success in c…
Recently, GAN-based neural vocoders such as Parallel WaveGAN, MelGAN, HiFiGAN, and UnivNet have become popular due to their lightweight and parallel structure, resulting in a real-time synthesized waveform with high fidelity, even on a CPU. HiFiGAN and UnivNet are two SOTA vocoders. Despite their high quality, there is still room for improvement. In this paper, motivated by the structure of Vision Outlooker from computer vision, we adopt a similar idea and propose an effective and lightweight neural vocoder called WOLONet. In this network, we develop a novel lightweight block that uses a locat…
We propose using self-supervised discrete representations for the task of speech resynthesis. To generate disentangled representation, we separately extract low-bitrate representations for speech content, prosodic information, and speaker identity. This allows to synthesize speech in a controllable manner. We analyze various state-of-the-art, self-supervised representation learning methods and shed light on the advantages of each method while considering reconstruction quality and disentanglement properties. Specifically, we evaluate the F0 reconstruction, speaker identification performance (f…
In this work, we propose ParaNet, a non-autoregressive seq2seq model that converts text to spectrogram. It is fully convolutional and brings 46.7 times speed-up over the lightweight Deep Voice 3 at synthesis, while obtaining reasonably good speech quality. ParaNet also produces stable alignment between text and speech on the challenging test sentences by iteratively improving the attention in a layer-by-layer manner. Furthermore, we build the parallel text-to-speech system and test various parallel neural vocoders, which can synthesize speech from text through a single feed-forward pass. We al…
Non-autoregressive text-to-speech (NAR-TTS) models such as FastSpeech 2 and Glow-TTS can synthesize high-quality speech from the given text in parallel. After analyzing two kinds of generative NAR-TTS models (VAE and normalizing flow), we find that: VAE is good at capturing the long-range semantics features (e.g., prosody) even with small model size but suffers from blurry and unnatural results; and normalizing flow is good at reconstructing the frequency bin-wise details but performs poorly when the number of model parameters is limited. Inspired by these observations, to generate diverse spe…
NTT Communication Science Laboratories, NTT Corporation（日本电信电话株式会社通信科学实验室）
In recent text-to-speech synthesis and voice conversion systems, a mel-spectrogram is commonly applied as an intermediate representation, and the necessity for a mel-spectrogram vocoder is increasing. A mel-spectrogram vocoder must solve three inverse problems: recovery of the original-scale magnitude spectrogram, phase reconstruction, and frequency-to-time conversion. A typical convolutional mel-spectrogram vocoder solves these problems jointly and implicitly using a convolutional neural network, including temporal upsampling layers, when directly calculating a raw waveform. Such an approach …
Codec-SUPERB @ SLT 2024: A lightweight benchmark for neural audio codec models
National Taiwan University（台湾大学）；Massachusetts Institute of Technology（麻省理工学院）；Microsoft Corporation（微软公司）；Meta；The Chinese University of Hong Kong（香港中文大学）；Carnegie Mellon University（卡内基梅隆大学）
Electronics and Telecommunications Research Institute（韩国电子通信研究院）
Low and ultra-low-bitrate neural speech coding achieves unprecedented coding gain by generating speech signals from compact speech features. This paper introduces additional coding efficiency in neural speech coding by reducing the temporal redundancy existing in the frame-level feature sequence via a recurrent neural predictor. The prediction can achieve a low-entropy residual representation, which we discriminatively code based on their contribution to the signal reconstruction. The harmonization of feature prediction and discriminative coding results in a dynamic bit allocation algorithm th…
Renmin University of China（中国人民大学）；University of Science and Technology of China（中国科学技术大学）；South China University of Technology（华南理工大学）；University of Surrey（萨里大学）；MSRA（微软亚洲研究院）；Microsoft Azure Speech（微软Azure语音）；Imperial College London（帝国理工学院）
Denoising Diffusion Probabilistic Models (DDPMs) are emerging in text-to-speech (TTS) synthesis because of their strong capability of generating high-fidelity samples. However, their iterative refinement process in high-dimensional data space results in slow inference speed, which restricts their application in real-time systems. Previous works have explored speeding up by minimizing the number of inference steps but at the cost of sample quality. In this work, to improve the inference speed for DDPM-based TTS model while achieving high sample quality, we propose ResGrad, a lightweight diffusi…
This paper introduces a new method referred to as KISS-GEV (for Keep It Super Simple Generalized eigenvalue) beamforming. While GEV beamforming usually relies on deep neural network for estimating target and noise time-frequency masks, this method uses a signal processing approach based on the direction of arrival (DoA) of the target. This considerably reduces the amount of computations involved at test time, and works for speech enhancement in unseen conditions as there is no need to train a neural network with noisy speech. The proposed method can also be used to separate speech from a mixtu…
Self-supervised learning method that provides generalized speech representations has recently received increasing attention. Wav2vec 2.0 is the most famous example, showing remarkable performance in numerous downstream speech processing tasks. Despite its success, it is challenging to use it directly for wake-up word detection on mobile devices due to its expensive computational cost. In this work, we propose LiteFEW, a lightweight feature encoder for wake-up word detection that preserves the inherent ability of wav2vec 2.0 with a minimum scale. In the method, the knowledge of the pre-trained …
Model size and complexity remain the biggest challenges in the deployment of speech enhancement and separation systems on low-resource devices such as earphones and hearing aids. Although methods such as compression, distillation and quantization can be applied to large models, they often come with a cost on the model performance. In this paper, we provide a simple model design paradigm that explicitly designs ultra-lightweight models without sacrificing the performance. Motivated by the sub-band frequency-LSTM (F-LSTM) architectures, we introduce the group communication (GroupComm), where a f…
