Gull: A Generative Multifunctional Audio Codec

We introduce Gull, a generative multifunctional audio codec. Gull is a general purpose neural audio compression and decompression model which can be applied to a wide range of tasks and applications such as real-time communication, audio super-resolution, and codec language models. The key components of Gull include (1) universal-sample-rate modeling via subband modeling schemes motivated by recent progress in audio source separation, (2) gain-shape representations motivated by traditional audio codecs, (3) improved residual vector quantization modules for simpler training, (4) elastic decoder network that enables user-defined model size and complexity during inference time, (5) built-in ability for audio super-resolution without the increase of bitrate. We compare Gull with existing traditional and neural audio codecs and show that Gull is able to achieve on par or better performance across various sample rates, bitrates and model complexities in both subjective and objective evaluation metrics.

Continuous Target Speech Extraction: Enhancing Personalized Diarization and Extraction on Complex Recordings

Target speaker extraction (TSE) aims to extract the target speaker's voice from the input mixture. Previous studies have concentrated on high-overlapping scenarios. However, real-world applications usually meet more complex scenarios like variable speaker overlapping and target speaker absence. In this paper, we introduces a framework to perform continuous TSE (C-TSE), comprising a target speaker voice activation detection (TSVAD) and a TSE model. This framework significantly improves TSE performance on similar speakers and enhances personalization, which is lacking in traditional diarization methods. In detail, unlike conventional TSVAD deployed to refine the diarization results, the proposed Attention-target speaker voice activation detection (A-TSVAD) directly generates timestamps of the target speaker. We also explore some different integration methods of A-TSVAD and TSE by comparing the cascaded and parallel methods. The framework's effectiveness is assessed using a range of metrics, including diarization and enhancement metrics. Our experiments demonstrate that A-TSVAD outperforms conventional methods in reducing diarization errors. Furthermore, the integration of A-TSVAD and TSE in a sequential cascaded manner further enhances extraction accuracy.

Consistent and Relevant: Rethink the Query Embedding in General Sound Separation

The query-based audio separation usually employs specific queries to extract target sources from a mixture of audio signals. Currently, most query-based separation models need additional networks to obtain query embedding. In this way, separation model is optimized to be adapted to the distribution of query embedding. However, query embedding may exhibit mismatches with separation models due to inconsistent structures and independent information. In this paper, we present CaRE-SEP, a consistent and relevant embedding network for general sound separation to encourage a comprehensive reconsideration of query usage in audio separation. CaRE-SEP alleviates the potential mismatch between queries and separation in two aspects, including sharing network structure and sharing feature information. First, a Swin-Unet model with a shared encoder is conducted to unify query encoding and sound separation into one model, eliminating the network architecture difference and generating consistent distribution of query and separation features. Second, by initializing CaRE-SEP with a pretrained classification network and allowing gradient backpropagation, the query embedding is optimized to be relevant to the separation feature, further alleviating the feature mismatch problem. Experimental results indicate the proposed CaRE-SEP model substantially improves the performance of separation tasks. Moreover, visualizations validate the potential mismatch and how CaRE-SEP solves it.

SECap: Speech Emotion Captioning with Large Language Model

Speech emotions are crucial in human communication and are extensively used in fields like speech synthesis and natural language understanding. Most prior studies, such as speech emotion recognition, have categorized speech emotions into a fixed set of classes. Yet, emotions expressed in human speech are often complex, and categorizing them into predefined groups can be insufficient to adequately represent speech emotions. On the contrary, describing speech emotions directly by means of natural language may be a more effective approach. Regrettably, there are not many studies available that have focused on this direction. Therefore, this paper proposes a speech emotion captioning framework named SECap, aiming at effectively describing speech emotions using natural language. Owing to the impressive capabilities of large language models in language comprehension and text generation, SECap employs LLaMA as the text decoder to allow the production of coherent speech emotion captions. In addition, SECap leverages HuBERT as the audio encoder to extract general speech features and Q-Former as the Bridge-Net to provide LLaMA with emotion-related speech features. To accomplish this, Q-Former utilizes mutual information learning to disentangle emotion-related speech features and speech contents, while implementing contrastive learning to extract more emotion-related speech features. The results of objective and subjective evaluations demonstrate that: 1) the SECap framework outperforms the HTSAT-BART baseline in all objective evaluations; 2) SECap can generate high-quality speech emotion captions that attain performance on par with human annotators in subjective mean opinion score tests.

AutoPrep: An Automatic Preprocessing Framework for In-the-Wild Speech Data

Recently, the utilization of extensive open-sourced text data has significantly advanced the performance of text-based large language models (LLMs). However, the use of in-the-wild large-scale speech data in the speech technology community remains constrained. One reason for this limitation is that a considerable amount of the publicly available speech data is compromised by background noise, speech overlapping, lack of speech segmentation information, missing speaker labels, and incomplete transcriptions, which can largely hinder their usefulness. On the other hand, human annotation of speech data is both time-consuming and costly. To address this issue, we introduce an automatic in-the-wild speech data preprocessing framework (AutoPrep) in this paper, which is designed to enhance speech quality, generate speaker labels, and produce transcriptions automatically. The proposed AutoPrep framework comprises six components: speech enhancement, speech segmentation, speaker clustering, target speech extraction, quality filtering and automatic speech recognition. Experiments conducted on the open-sourced WenetSpeech and our self-collected AutoPrepWild corpora demonstrate that the proposed AutoPrep framework can generate preprocessed data with similar DNSMOS and PDNSMOS scores compared to several open-sourced TTS datasets. The corresponding TTS system can achieve up to 0.68 in-domain speaker similarity.

Complexity Scaling for Speech Denoising

Computational complexity is critical when deploying deep learning-based speech denoising models for on-device applications. Most prior research focused on optimizing model architectures to meet specific computational cost constraints, often creating distinct neural network architectures for different complexity limitations. This study conducts complexity scaling for speech denoising tasks, aiming to consolidate models with various complexities into a unified architecture. We present a Multi-Path Transform-based (MPT) architecture to handle both low- and high-complexity scenarios. A series of MPT networks present high performance covering a wide range of computational complexities on the DNS challenge dataset. Moreover, inspired by the scaling experiments in natural language processing, we explore the empirical relationship between model performance and computational cost on the denoising task. As the complexity number of multiply-accumulate operations (MACs) is scaled from 50M/s to 15G/s on MPT networks, we observe a linear increase in the values of PESQ-WB and SI-SNR, proportional to the logarithm of MACs, which might contribute to the understanding and application of complexity scaling in speech denoising tasks.

Ultra Dual-Path Compression For Joint Echo Cancellation And Noise Suppression

Echo cancellation and noise reduction are essential for full-duplex communication, yet most existing neural networks have high computational costs and are inflexible in tuning model complexity. In this paper, we introduce time-frequency dual-path compression to achieve a wide range of compression ratios on computational cost. Specifically, for frequency compression, trainable filters are used to replace manually designed filters for dimension reduction. For time compression, only using frame skipped prediction causes large performance degradation, which can be alleviated by a post-processing network with full sequence modeling. We have found that under fixed compression ratios, dual-path compression combining both the time and frequency methods will give further performance improvement, covering compression ratios from 4x to 32x with little model size change. Moreover, the proposed models show competitive performance compared with fast FullSubNet and DeepFilterNet. A demo page can be found at hangtingchen.github.io/ultra_dual_path_compression.github.io/.

Bayes Risk Transducer: Transducer with Controllable Alignment Prediction

Automatic speech recognition (ASR) based on transducers is widely used. In training, a transducer maximizes the summed posteriors of all paths. The path with the highest posterior is commonly defined as the predicted alignment between the speech and the transcription. While the vanilla transducer does not have a prior preference for any of the valid paths, this work intends to enforce the preferred paths and achieve controllable alignment prediction. Specifically, this work proposes Bayes Risk Transducer (BRT), which uses a Bayes risk function to set lower risk values to the preferred paths so that the predicted alignment is more likely to satisfy specific desired properties. We further demonstrate that these predicted alignments with intentionally designed properties can provide practical advantages over the vanilla transducer. Experimentally, the proposed BRT saves inference cost by up to 46% for non-streaming ASR and reduces overall system latency by 41% for streaming ASR.

High Fidelity Speech Enhancement with Band-split RNN

This report presents the development of our speech enhancement system, which includes the use of a recently proposed music separation model, the band-split recurrent neural network (BSRNN), and a MetricGAN-based training objective to improve non-differentiable quality metrics such as perceptual evaluation of speech quality (PESQ) score. Experiment conducted on Interspeech 2021 DNS challenge shows that our BSRNN system outperforms various top-ranking benchmark systems in previous deep noise suppression (DNS) challenges and achieves state-of-the-art (SOTA) result on the DNS-2020 non-blind test set in both offline and online scenarios.

The HCCL System for the NIST SRE21

This paper describes the systems developed by the HCCL team for the NIST 2021 speaker recognition evaluation (NIST SRE21).We first explore various state-of-the-art speaker embedding extractors combined with a novel circle loss to obtain discriminative deep speaker embeddings. Considering that cross-channel and cross-linguistic speaker recognition are the key challenges of SRE21, we introduce several techniques to reduce the cross-domain mismatch. Specifically, Codec and speech enhancement are directly applied to the raw speech to eliminate the codecs and the environment noise mismatch. We denote the methods that work directly on speech to eliminate the relatively explicit mismatches collectively as data adaptation methods. Experiments show that data adaption methods achieve 15\% improvements over our baseline. Furthermore, some popular back-ends domain adaptation algorithms are deployed on speaker embeddings to alleviate speaker performance degradation caused by the implicit mismatch. Score calibration is a major failure for us in SRE21. The reason is that score calibration with too many parameters easily lead to overfitting problems.