EmoPro: A Prompt Selection Strategy for Emotional Expression in LM-based Speech Synthesis

Recent advancements in speech synthesis models, trained on extensive datasets, have demonstrated remarkable zero-shot capabilities. These models can control content, timbre, and emotion in generated speech based on prompt inputs. Despite these advancements, the choice of prompts significantly impacts the output quality, yet most existing selection schemes do not adequately address the control of emotional intensity. To address this question, this paper proposes a two-stage prompt selection strategy EmoPro, which is specifically designed for emotionally controllable speech synthesis. This strategy focuses on selecting highly expressive and high-quality prompts by evaluating them from four perspectives: emotional expression strength, speech quality, text-emotion consistency, and model generation performance. Experimental results show that prompts selected using the proposed method result in more emotionally expressive and engaging synthesized speech compared to those obtained through baseline. Audio samples and codes will be available at https://whyrrrrun.github.io/EmoPro/.

Progressive Residual Extraction based Pre-training for Speech Representation Learning

Self-supervised learning (SSL) has garnered significant attention in speech processing, excelling in linguistic tasks such as speech recognition. However, jointly improving the performance of pre-trained models on various downstream tasks, each requiring different speech information, poses significant challenges. To this purpose, we propose a progressive residual extraction based self-supervised learning method, named ProgRE. Specifically, we introduce two lightweight and specialized task modules into an encoder-style SSL backbone to enhance its ability to extract pitch variation and speaker information from speech. Furthermore, to prevent the interference of reinforced pitch variation and speaker information with irrelevant content information learning, we residually remove the information extracted by these two modules from the main branch. The main branch is then trained using HuBERT's speech masking prediction to ensure the performance of the Transformer's deep-layer features on content tasks. In this way, we can progressively extract pitch variation, speaker, and content representations from the input speech. Finally, we can combine multiple representations with diverse speech information using different layer weights to obtain task-specific representations for various downstream tasks. Experimental results indicate that our proposed method achieves joint performance improvements on various tasks, such as speaker identification, speech recognition, emotion recognition, speech enhancement, and voice conversion, compared to excellent SSL methods such as wav2vec2.0, HuBERT, and WavLM.

VQ-CTAP: Cross-Modal Fine-Grained Sequence Representation Learning for Speech Processing

Deep learning has brought significant improvements to the field of cross-modal representation learning. For tasks such as text-to-speech (TTS), voice conversion (VC), and automatic speech recognition (ASR), a cross-modal fine-grained (frame-level) sequence representation is desired, emphasizing the semantic content of the text modality while de-emphasizing the paralinguistic information of the speech modality. We propose a method called "Vector Quantized Contrastive Token-Acoustic Pre-training (VQ-CTAP)", which uses the cross-modal aligned sequence transcoder to bring text and speech into a joint multimodal space, learning how to connect text and speech at the frame level. The proposed VQ-CTAP is a paradigm for cross-modal sequence representation learning, offering a promising solution for fine-grained generation and recognition tasks in speech processing. The VQ-CTAP can be directly applied to VC and ASR tasks without fine-tuning or additional structures. We propose a sequence-aware semantic connector, which connects multiple frozen pre-trained modules for the TTS task, exhibiting a plug-and-play capability. We design a stepping optimization strategy to ensure effective model convergence by gradually injecting and adjusting the influence of various loss components. Furthermore, we propose a semantic-transfer-wise paralinguistic consistency loss to enhance representational capabilities, allowing the model to better generalize to unseen data and capture the nuances of paralinguistic information. In addition, VQ-CTAP achieves high-compression speech coding at a rate of 25Hz from 24kHz input waveforms, which is a 960-fold reduction in the sampling rate. The audio demo is available at https://qiangchunyu.github.io/VQCTAP/

A Refining Underlying Information Framework for Monaural Speech Enhancement

Supervised speech enhancement has gained significantly from recent advancements in neural networks, especially due to their ability to non-linearly fit the diverse representations of target speech, such as waveform or spectrum. However, these direct-fitting solutions continue to face challenges with degraded speech and residual noise in hearing evaluations. By bridging the speech enhancement and the Information Bottleneck principle in this letter, we rethink a universal plug-and-play strategy and propose a Refining Underlying Information framework called RUI to rise to the challenges both in theory and practice. Specifically, we first transform the objective of speech enhancement into an incremental convergence problem of mutual information between comprehensive speech characteristics and individual speech characteristics, e.g., spectral and acoustic characteristics. By doing so, compared with the existing direct-fitting solutions, the underlying information stems from the conditional entropy of acoustic characteristic given spectral characteristics. Therefore, we design a dual-path multiple refinement iterator based on the chain rule of entropy to refine this underlying information for further approximating target speech. Experimental results on DNS-Challenge dataset show that our solution consistently improves 0.3+ PESQ score over baselines, with only additional 1.18 M parameters. The source code is available at https://github.com/caoruitju/RUI_SE.

On decoder-only architecture for speech-to-text and large language model integration

Large language models (LLMs) have achieved remarkable success in the field of natural language processing, enabling better human-computer interaction using natural language. However, the seamless integration of speech signals into LLMs has not been explored well. The "decoder-only" architecture has also not been well studied for speech processing tasks. In this research, we introduce Speech-LLaMA, a novel approach that effectively incorporates acoustic information into text-based large language models. Our method leverages Connectionist Temporal Classification and a simple audio encoder to map the compressed acoustic features to the continuous semantic space of the LLM. In addition, we further probe the decoder-only architecture for speech-to-text tasks by training a smaller scale randomly initialized speech-LLaMA model from speech-text paired data alone. We conduct experiments on multilingual speech-to-text translation tasks and demonstrate a significant improvement over strong baselines, highlighting the potential advantages of decoder-only models for speech-to-text conversion.

VioLA: Unified Codec Language Models for Speech Recognition, Synthesis, and Translation

Recent research shows a big convergence in model architecture, training objectives, and inference methods across various tasks for different modalities. In this paper, we propose VioLA, a single auto-regressive Transformer decoder-only network that unifies various cross-modal tasks involving speech and text, such as speech-to-text, text-to-text, text-to-speech, and speech-to-speech tasks, as a conditional codec language model task via multi-task learning framework. To accomplish this, we first convert all the speech utterances to discrete tokens (similar to the textual data) using an offline neural codec encoder. In such a way, all these tasks are converted to token-based sequence conversion problems, which can be naturally handled with one conditional language model. We further integrate task IDs (TID) and language IDs (LID) into the proposed model to enhance the modeling capability of handling different languages and tasks. Experimental results demonstrate that the proposed VioLA model can support both single-modal and cross-modal tasks well, and the decoder-only model achieves a comparable and even better performance than the strong baselines.

An Adapter based Multi-label Pre-training for Speech Separation and Enhancement

In recent years, self-supervised learning (SSL) has achieved tremendous success in various speech tasks due to its power to extract representations from massive unlabeled data. However, compared with tasks such as speech recognition (ASR), the improvements from SSL representation in speech separation (SS) and enhancement (SE) are considerably smaller. Based on HuBERT, this work investigates improving the SSL model for SS and SE. We first update HuBERT's masked speech prediction (MSP) objective by integrating the separation and denoising terms, resulting in a multiple pseudo label pre-training scheme, which significantly improves HuBERT's performance on SS and SE but degrades the performance on ASR. To maintain its performance gain on ASR, we further propose an adapter-based architecture for HuBERT's Transformer encoder, where only a few parameters of each layer are adjusted to the multiple pseudo label MSP while other parameters remain frozen as default HuBERT. Experimental results show that our proposed adapter-based multiple pseudo label HuBERT yield consistent and significant performance improvements on SE, SS, and ASR tasks, with a faster pre-training speed, at only marginal parameters increase.

A CTC Triggered Siamese Network with Spatial-Temporal Dropout for Speech Recognition

Siamese networks have shown effective results in unsupervised visual representation learning. These models are designed to learn an invariant representation of two augmentations for one input by maximizing their similarity. In this paper, we propose an effective Siamese network to improve the robustness of End-to-End automatic speech recognition (ASR). We introduce spatial-temporal dropout to support a more violent disturbance for Siamese-ASR framework. Besides, we also relax the similarity regularization to maximize the similarities of distributions on the frames that connectionist temporal classification (CTC) spikes occur rather than on all of them. The efficiency of the proposed architecture is evaluated on two benchmarks, AISHELL-1 and Librispeech, resulting in 7.13% and 6.59% relative character error rate (CER) and word error rate (WER) reductions respectively. Analysis shows that our proposed approach brings a better uniformity for the trained model and enlarges the CTC spikes obviously.

Multiple Confidence Gates For Joint Training Of SE And ASR

Joint training of speech enhancement model (SE) and speech recognition model (ASR) is a common solution for robust ASR in noisy environments. SE focuses on improving the auditory quality of speech, but the enhanced feature distribution is changed, which is uncertain and detrimental to the ASR. To tackle this challenge, an approach with multiple confidence gates for jointly training of SE and ASR is proposed. A speech confidence gates prediction module is designed to replace the former SE module in joint training. The noisy speech is filtered by gates to obtain features that are easier to be fitting by the ASR network. The experimental results show that the proposed method has better performance than the traditional robust speech recognition system on test sets of clean speech, synthesized noisy speech, and real noisy speech.

Harmonic gated compensation network plus for ICASSP 2022 DNS CHALLENGE

The harmonic structure of speech is resistant to noise, but the harmonics may still be partially masked by noise. Therefore, we previously proposed a harmonic gated compensation network (HGCN) to predict the full harmonic locations based on the unmasked harmonics and process the result of a coarse enhancement module to recover the masked harmonics. In addition, the auditory loudness loss function is used to train the network. For the DNS Challenge, we update HGCN with the following aspects, resulting in HGCN+. First, a high-band module is employed to help the model handle full-band signals. Second, cosine is used to model the harmonic structure more accurately. Then, the dual-path encoder and dual-path rnn (DPRNN) are introduced to take full advantage of the features. Finally, a gated residual linear structure replaces the gated convolution in the compensation module to increase the receptive field of frequency. The experimental results show that each updated module brings performance improvement to the model. HGCN+ also outperforms the referenced models on both wide-band and full-band test sets.