VoiceBench: Benchmarking LLM-Based Voice Assistants

Building on the success of large language models (LLMs), recent advancements such as GPT-4o have enabled real-time speech interactions through LLM-based voice assistants, offering a significantly improved user experience compared to traditional text-based interactions. However, the absence of benchmarks designed to evaluate these speech interaction capabilities has hindered progress of LLM-based voice assistants development. Current evaluations focus primarily on automatic speech recognition (ASR) or general knowledge evaluation with clean speeches, neglecting the more intricate, real-world scenarios that involve diverse speaker characteristics, environmental and content factors. To address this, we introduce VoiceBench, the first benchmark designed to provide a multi-faceted evaluation of LLM-based voice assistants. VoiceBench also includes both real and synthetic spoken instructions that incorporate the above three key real-world variations. Extensive experiments reveal the limitations of current LLM-based voice assistant models and offer valuable insights for future research and development in this field.

Beyond Single-Audio: Advancing Multi-Audio Processing in Audio Large Language Models

Various audio-LLMs (ALLMs) have been explored recently for tackling different audio tasks simultaneously using a single, unified model. While existing evaluations of ALLMs primarily focus on single-audio tasks, real-world applications often involve processing multiple audio streams simultaneously. To bridge this gap, we propose the first multi-audio evaluation (MAE) benchmark that consists of 20 datasets from 11 multi-audio tasks encompassing both speech and sound scenarios. Comprehensive experiments on MAE demonstrate that the existing ALLMs, while being powerful in comprehending primary audio elements in individual audio inputs, struggling to handle multi-audio scenarios. To this end, we propose a novel multi-audio-LLM (MALLM) to capture audio context among multiple similar audios using discriminative learning on our proposed synthetic data. The results demonstrate that the proposed MALLM outperforms all baselines and achieves high data efficiency using synthetic data without requiring human annotations. The proposed MALLM opens the door for ALLMs towards multi-audio processing era and brings us closer to replicating human auditory capabilities in machines.

Analytic Class Incremental Learning for Sound Source Localization with Privacy Protection

Sound Source Localization (SSL) enabling technology for applications such as surveillance and robotics. While traditional Signal Processing (SP)-based SSL methods provide analytic solutions under specific signal and noise assumptions, recent Deep Learning (DL)-based methods have significantly outperformed them. However, their success depends on extensive training data and substantial computational resources. Moreover, they often rely on large-scale annotated spatial data and may struggle when adapting to evolving sound classes. To mitigate these challenges, we propose a novel Class Incremental Learning (CIL) approach, termed SSL-CIL, which avoids serious accuracy degradation due to catastrophic forgetting by incrementally updating the DL-based SSL model through a closed-form analytic solution. In particular, data privacy is ensured since the learning process does not revisit any historical data (exemplar-free), which is more suitable for smart home scenarios. Empirical results in the public SSLR dataset demonstrate the superior performance of our proposal, achieving a localization accuracy of 90.9%, surpassing other competitive methods.

TTSlow: Slow Down Text-to-Speech with Efficiency Robustness Evaluations

Text-to-speech (TTS) has been extensively studied for generating high-quality speech with textual inputs, playing a crucial role in various real-time applications. For real-world deployment, ensuring stable and timely generation in TTS models against minor input perturbations is of paramount importance. Therefore, evaluating the robustness of TTS models against such perturbations, commonly known as adversarial attacks, is highly desirable. In this paper, we propose TTSlow, a novel adversarial approach specifically tailored to slow down the speech generation process in TTS systems. To induce long TTS waiting time, we design novel efficiency-oriented adversarial loss to encourage endless generation process. TTSlow encompasses two attack strategies targeting both text inputs and speaker embedding. Specifically, we propose TTSlow-text, which utilizes a combination of homoglyphs-based and swap-based perturbations, along with TTSlow-spk, which employs a gradient optimization attack approach for speaker embedding. TTSlow serves as the first attack approach targeting a wide range of TTS models, including autoregressive and non-autoregressive TTS ones, thereby advancing exploration in audio security. Extensive experiments are conducted to evaluate the inference efficiency of TTS models, and in-depth analysis of generated speech intelligibility is performed using Gemini. The results demonstrate that TTSlow can effectively slow down two TTS models across three publicly available datasets. We are committed to releasing the source code upon acceptance, facilitating further research and benchmarking in this domain.

Text-guided HuBERT: Self-Supervised Speech Pre-training via Generative Adversarial Networks

Human language can be expressed in either written or spoken form, i.e. text or speech. Humans can acquire knowledge from text to improve speaking and listening. However, the quest for speech pre-trained models to leverage unpaired text has just started. In this paper, we investigate a new way to pre-train such a joint speech-text model to learn enhanced speech representations and benefit various speech-related downstream tasks. Specifically, we propose a novel pre-training method, text-guided HuBERT, or T-HuBERT, which performs self-supervised learning over speech to derive phoneme-like discrete representations. And these phoneme-like pseudo-label sequences are firstly derived from speech via the generative adversarial networks (GAN) to be statistically similar to those from additional unpaired textual data. In this way, we build a bridge between unpaired speech and text in an unsupervised manner. Extensive experiments demonstrate the significant superiority of our proposed method over various strong baselines, which achieves up to 15.3% relative Word Error Rate (WER) reduction on the LibriSpeech dataset.

CoAVT: A Cognition-Inspired Unified Audio-Visual-Text Pre-Training Model for Multimodal Processing

There has been a long-standing quest for a unified audio-visual-text model to enable various multimodal understanding tasks, which mimics the listening, seeing and reading process of human beings. Humans tends to represent knowledge using two separate systems: one for representing verbal (textual) information and one for representing non-verbal (visual and auditory) information. These two systems can operate independently but can also interact with each other. Motivated by this understanding of human cognition, in this paper, we introduce CoAVT -- a novel cognition-inspired Correlated Audio-Visual-Text pre-training model to connect the three modalities. It contains a joint audio-visual encoder that learns to encode audio-visual synchronization information together with the audio and visual content for non-verbal information, and a text encoder to handle textual input for verbal information. To bridge the gap between modalities, CoAVT employs a query encoder, which contains a set of learnable query embeddings, and extracts the most informative audiovisual features of the corresponding text. Additionally, to leverage the correspondences between audio and vision with language respectively, we also establish the audio-text and visual-text bi-modal alignments upon the foundational audiovisual-text tri-modal alignment to enhance the multimodal representation learning. Finally, we jointly optimize CoAVT model with three multimodal objectives: contrastive loss, matching loss and language modeling loss. Extensive experiments show that CoAVT can learn strong multimodal correlations and be generalized to various downstream tasks. CoAVT establishes new state-of-the-art performance on text-video retrieval task on AudioCaps for both zero-shot and fine-tuning settings, audio-visual event classification and audio-visual retrieval tasks on AudioSet and VGGSound.

Self-Supervised Acoustic Word Embedding Learning via Correspondence Transformer Encoder

Acoustic word embeddings (AWEs) aims to map a variable-length speech segment into a fixed-dimensional representation. High-quality AWEs should be invariant to variations, such as duration, pitch and speaker. In this paper, we introduce a novel self-supervised method to learn robust AWEs from a large-scale unlabelled speech corpus. Our model, named Correspondence Transformer Encoder (CTE), employs a teacher-student learning framework. We train the model based on the idea that different realisations of the same word should be close in the underlying embedding space. Specifically, we feed the teacher and student encoder with different acoustic instances of the same word and pre-train the model with a word-level loss. Our experiments show that the embeddings extracted from the proposed CTE model are robust to speech variations, e.g. speakers and domains. Additionally, when evaluated on Xitsonga, a low-resource cross-lingual setting, the CTE model achieves new state-of-the-art performance.

Self-Transriber: Few-shot Lyrics Transcription with Self-training

The current lyrics transcription approaches heavily rely on supervised learning with labeled data, but such data are scarce and manual labeling of singing is expensive. How to benefit from unlabeled data and alleviate limited data problem have not been explored for lyrics transcription. We propose the first semi-supervised lyrics transcription paradigm, Self-Transcriber, by leveraging on unlabeled data using self-training with noisy student augmentation. We attempt to demonstrate the possibility of lyrics transcription with a few amount of labeled data. Self-Transcriber generates pseudo labels of the unlabeled singing using teacher model, and augments pseudo-labels to the labeled data for student model update with both self-training and supervised training losses. This work closes the gap between supervised and semi-supervised learning as well as opens doors for few-shot learning of lyrics transcription. Our experiments show that our approach using only 12.7 hours of labeled data achieves competitive performance compared with the supervised approaches trained on 149.1 hours of labeled data for lyrics transcription.

token2vec: A Joint Self-Supervised Pre-training Framework Using Unpaired Speech and Text

Self-supervised pre-training has been successful in both text and speech processing. Speech and text offer different but complementary information. The question is whether we are able to perform a speech-text joint pre-training on unpaired speech and text. In this paper, we take the idea of self-supervised pre-training one step further and propose token2vec, a novel joint pre-training framework for unpaired speech and text based on discrete representations of speech. Firstly, due to the distinct characteristics between speech and text modalities, where speech is continuous while text is discrete, we first discretize speech into a sequence of discrete speech tokens to solve the modality mismatch problem. Secondly, to solve the length mismatch problem, where the speech sequence is usually much longer than text sequence, we convert the words of text into phoneme sequences and randomly repeat each phoneme in the sequences. Finally, we feed the discrete speech and text tokens into a modality-agnostic Transformer encoder and pre-train with token-level masking language modeling (tMLM). Experiments show that token2vec is significantly superior to various speech-only pre-training baselines, with up to 17.7% relative WER reduction. Token2vec model is also validated on a non-ASR task, i.e., spoken intent classification, and shows good transferability.

End-to-End Code-Switching ASR for Low-Resourced Language Pairs

Despite the significant progress in end-to-end (E2E) automatic speech recognition (ASR), E2E ASR for low resourced code-switching (CS) speech has not been well studied. In this work, we describe an E2E ASR pipeline for the recognition of CS speech in which a low-resourced language is mixed with a high resourced language. Low-resourcedness in acoustic data hinders the performance of E2E ASR systems more severely than the conventional ASR systems.~To mitigate this problem in the transcription of archives with code-switching Frisian-Dutch speech, we integrate a designated decoding scheme and perform rescoring with neural network-based language models to enable better utilization of the available textual resources. We first incorporate a multi-graph decoding approach which creates parallel search spaces for each monolingual and mixed recognition tasks to maximize the utilization of the textual resources from each language. Further, language model rescoring is performed using a recurrent neural network pre-trained with cross-lingual embedding and further adapted with the limited amount of in-domain CS text. The ASR experiments demonstrate the effectiveness of the described techniques in improving the recognition performance of an E2E CS ASR system in a low-resourced scenario.