Gopala K. Anumanchipalli

Xuanru Zhou, Anshul Kashyap, Steve Li et al.

Dysfluent speech detection is the bottleneck for disordered speech analysis and spoken language learning. Current state-of-the-art models are governed by rule-based systems which lack efficiency and robustness, and are sensitive to template design. In this paper, we propose YOLO-Stutter: a first end-to-end method that detects dysfluencies in a time-accurate manner. YOLO-Stutter takes imperfect speech-text alignment as input, followed by a spatial feature aggregator, and a temporal dependency extractor to perform region-wise boundary and class predictions. We also introduce two dysfluency corpus, VCTK-Stutter and VCTK-TTS, that simulate natural spoken dysfluencies including repetition, block, missing, replacement, and prolongation. Our end-to-end method achieves state-of-the-art performance with a minimum number of trainable parameters for on both simulated data and real aphasia speech. Code and datasets are open-sourced at https://github.com/rorizzz/YOLO-Stutter

Lutfi Eren Erdogan, Nicholas Lee, Siddharth Jha et al.

Recent large language models (LLMs) have enabled the development of advanced agentic systems that can integrate various tools and APIs to fulfill user queries through function calling. However, the deployment of these LLMs on the edge has not been explored since they typically require cloud-based infrastructure due to their substantial model size and computational demands. To this end, we present TinyAgent, an end-to-end framework for training and deploying task-specific small language model agents capable of function calling for driving agentic systems at the edge. We first show how to enable accurate function calling for open-source models via the LLMCompiler framework. We then systematically curate a high-quality dataset for function calling, which we use to fine-tune two small language models, TinyAgent-1.1B and 7B. For efficient inference, we introduce a novel tool retrieval method to reduce the input prompt length and utilize quantization to further accelerate the inference speed. As a driving application, we demonstrate a local Siri-like system for Apple's MacBook that can execute user commands through text or voice input. Our results show that our models can achieve, and even surpass, the function-calling capabilities of larger models like GPT-4-Turbo, while being fully deployed at the edge. We open-source our dataset, models, and installable package and provide a demo video for our MacBook assistant agent.

Cheol Jun Cho, Abdelrahman Mohamed, Shang-Wen Li et al. · meta-ai, mit

Data-driven unit discovery in self-supervised learning (SSL) of speech has embarked on a new era of spoken language processing. Yet, the discovered units often remain in phonetic space and the units beyond phonemes are largely underexplored. Here, we demonstrate that a syllabic organization emerges in learning sentence-level representation of speech. In particular, we adopt "self-distillation" objective to fine-tune the pretrained HuBERT with an aggregator token that summarizes the entire sentence. Without any supervision, the resulting model draws definite boundaries in speech, and the representations across frames exhibit salient syllabic structures. We demonstrate that this emergent structure largely corresponds to the ground truth syllables. Furthermore, we propose a new benchmark task, Spoken Speech ABX, for evaluating sentence-level representation of speech. When compared to previous models, our model outperforms in both unsupervised syllable discovery and learning sentence-level representation. Together, we demonstrate that the self-distillation of HuBERT gives rise to syllabic organization without relying on external labels or modalities, and potentially provides novel data-driven units for spoken language modeling.

Jiachen Lian, Xuanru Zhou, Zoe Ezzes et al.

Speech dysfluency modeling is the core module for spoken language learning, and speech therapy. However, there are three challenges. First, current state-of-the-art solutions\cite{lian2023unconstrained-udm, lian-anumanchipalli-2024-towards-hudm} suffer from poor scalability. Second, there is a lack of a large-scale dysfluency corpus. Third, there is not an effective learning framework. In this paper, we propose \textit{SSDM: Scalable Speech Dysfluency Modeling}, which (1) adopts articulatory gestures as scalable forced alignment; (2) introduces connectionist subsequence aligner (CSA) to achieve dysfluency alignment; (3) introduces a large-scale simulated dysfluency corpus called Libri-Dys; and (4) develops an end-to-end system by leveraging the power of large language models (LLMs). We expect SSDM to serve as a standard in the area of dysfluency modeling. Demo is available at \url{https://berkeley-speech-group.github.io/SSDM/}.

Jiachen Lian, Alan W Black, Louis Goldstein et al.

Most of the research on data-driven speech representation learning has focused on raw audios in an end-to-end manner, paying little attention to their internal phonological or gestural structure. This work, investigating the speech representations derived from articulatory kinematics signals, uses a neural implementation of convolutive sparse matrix factorization to decompose the articulatory data into interpretable gestures and gestural scores. By applying sparse constraints, the gestural scores leverage the discrete combinatorial properties of phonological gestures. Phoneme recognition experiments were additionally performed to show that gestural scores indeed code phonological information successfully. The proposed work thus makes a bridge between articulatory phonology and deep neural networks to leverage informative, intelligible, interpretable,and efficient speech representations.

Cheol Jun Cho, Peter Wu, Abdelrahman Mohamed et al.

Recent self-supervised learning (SSL) models have proven to learn rich representations of speech, which can readily be utilized by diverse downstream tasks. To understand such utilities, various analyses have been done for speech SSL models to reveal which and how information is encoded in the learned representations. Although the scope of previous analyses is extensive in acoustic, phonetic, and semantic perspectives, the physical grounding by speech production has not yet received full attention. To bridge this gap, we conduct a comprehensive analysis to link speech representations to articulatory trajectories measured by electromagnetic articulography (EMA). Our analysis is based on a linear probing approach where we measure articulatory score as an average correlation of linear mapping to EMA. We analyze a set of SSL models selected from the leaderboard of the SUPERB benchmark and perform further layer-wise analyses on two most successful models, Wav2Vec 2.0 and HuBERT. Surprisingly, representations from the recent speech SSL models are highly correlated with EMA traces (best: r = 0.81), and only 5 minutes are sufficient to train a linear model with high performance (r = 0.77). Our findings suggest that SSL models learn to align closely with continuous articulations, and provide a novel insight into speech SSL.

Jiachen Lian, Chunlei Zhang, Gopala Krishna Anumanchipalli et al.

Disentangling content and speaking style information is essential for zero-shot non-parallel voice conversion (VC). Our previous study investigated a novel framework with disentangled sequential variational autoencoder (DSVAE) as the backbone for information decomposition. We have demonstrated that simultaneous disentangling content embedding and speaker embedding from one utterance is feasible for zero-shot VC. In this study, we continue the direction by raising one concern about the prior distribution of content branch in the DSVAE baseline. We find the random initialized prior distribution will force the content embedding to reduce the phonetic-structure information during the learning process, which is not a desired property. Here, we seek to achieve a better content embedding with more phonetic information preserved. We propose conditional DSVAE, a new model that enables content bias as a condition to the prior modeling and reshapes the content embedding sampled from the posterior distribution. In our experiment on the VCTK dataset, we demonstrate that content embeddings derived from the conditional DSVAE overcome the randomness and achieve a much better phoneme classification accuracy, a stabilized vocalization and a better zero-shot VC performance compared with the competitive DSVAE baseline.

Jiachen Lian, Chunlei Zhang, Gopala Krishna Anumanchipalli et al.

In this paper, we propose a novel unsupervised text-to-speech acoustic model training scheme, named UTTS, which does not require text-audio pairs. UTTS is a multi-speaker speech synthesizer that supports zero-shot voice cloning, it is developed from a perspective of disentangled speech representation learning. The framework offers a flexible choice of a speaker's duration model, timbre feature (identity) and content for TTS inference. We leverage recent advancements in self-supervised speech representation learning as well as speech synthesis front-end techniques for system development. Specifically, we employ our recently formulated Conditional Disentangled Sequential Variational Auto-encoder (C-DSVAE) as the backbone UTTS AM, which offers well-structured content representations given unsupervised alignment (UA) as condition during training. For UTTS inference, we utilize a lexicon to map input text to the phoneme sequence, which is expanded to the frame-level forced alignment (FA) with a speaker-dependent duration model. Then, we develop an alignment mapping module that converts FA to UA. Finally, the C-DSVAE, serving as the self-supervised TTS AM, takes the predicted UA and a target speaker embedding to generate the mel spectrogram, which is ultimately converted to waveform with a neural vocoder. We show how our method enables speech synthesis without using a paired TTS corpus in AM development stage. Experiments demonstrate that UTTS can synthesize speech of high naturalness and intelligibility measured by human and objective evaluations. Audio samples are available at our demo page https://neurtts.github.io/utts\_demo/.

Cheol Jun Cho, Abdelrahman Mohamed, Alan W Black et al.

Self-Supervised Learning (SSL) based models of speech have shown remarkable performance on a range of downstream tasks. These state-of-the-art models have remained blackboxes, but many recent studies have begun "probing" models like HuBERT, to correlate their internal representations to different aspects of speech. In this paper, we show "inference of articulatory kinematics" as fundamental property of SSL models, i.e., the ability of these models to transform acoustics into the causal articulatory dynamics underlying the speech signal. We also show that this abstraction is largely overlapping across the language of the data used to train the model, with preference to the language with similar phonological system. Furthermore, we show that with simple affine transformations, Acoustic-to-Articulatory inversion (AAI) is transferrable across speakers, even across genders, languages, and dialects, showing the generalizability of this property. Together, these results shed new light on the internals of SSL models that are critical to their superior performance, and open up new avenues into language-agnostic universal models for speech engineering, that are interpretable and grounded in speech science.

Cheol Jun Cho, Edward F. Chang, Gopala K. Anumanchipalli

Understanding the neural implementation of complex human behaviors is one of the major goals in neuroscience. To this end, it is crucial to find a true representation of the neural data, which is challenging due to the high complexity of behaviors and the low signal-to-ratio (SNR) of the signals. Here, we propose a novel unsupervised learning framework, Neural Latent Aligner (NLA), to find well-constrained, behaviorally relevant neural representations of complex behaviors. The key idea is to align representations across repeated trials to learn cross-trial consistent information. Furthermore, we propose a novel, fully differentiable time warping model (TWM) to resolve the temporal misalignment of trials. When applied to intracranial electrocorticography (ECoG) of natural speaking, our model learns better representations for decoding behaviors than the baseline models, especially in lower dimensional space. The TWM is empirically validated by measuring behavioral coherence between aligned trials. The proposed framework learns more cross-trial consistent representations than the baselines, and when visualized, the manifold reveals shared neural trajectories across trials.

Gašper Beguš, Alan Zhou, Peter Wu et al.

Generative deep neural networks are widely used for speech synthesis, but most existing models directly generate waveforms or spectral outputs. Humans, however, produce speech by controlling articulators, which results in the production of speech sounds through physical properties of sound propagation. We introduce the Articulatory Generator to the Generative Adversarial Network paradigm, a new unsupervised generative model of speech production/synthesis. The Articulatory Generator more closely mimics human speech production by learning to generate articulatory representations (electromagnetic articulography or EMA) in a fully unsupervised manner. A separate pre-trained physical model (ema2wav) then transforms the generated EMA representations to speech waveforms, which get sent to the Discriminator for evaluation. Articulatory analysis suggests that the network learns to control articulators in a similar manner to humans during speech production. Acoustic analysis of the outputs suggests that the network learns to generate words that are both present and absent in the training distribution. We additionally discuss implications of articulatory representations for cognitive models of human language and speech technology in general.

Yisi Liu, Bohan Yu, Drake Lin et al.

Articulatory trajectories like electromagnetic articulography (EMA) provide a low-dimensional representation of the vocal tract filter and have been used as natural, grounded features for speech synthesis. Differentiable digital signal processing (DDSP) is a parameter-efficient framework for audio synthesis. Therefore, integrating low-dimensional EMA features with DDSP can significantly enhance the computational efficiency of speech synthesis. In this paper, we propose a fast, high-quality, and parameter-efficient DDSP articulatory vocoder that can synthesize speech from EMA, F0, and loudness. We incorporate several techniques to solve the harmonics / noise imbalance problem, and add a multi-resolution adversarial loss for better synthesis quality. Our model achieves a transcription word error rate (WER) of 6.67% and a mean opinion score (MOS) of 3.74, with an improvement of 1.63% and 0.16 compared to the state-of-the-art (SOTA) baseline. Our DDSP vocoder is 4.9x faster than the baseline on CPU during inference, and can generate speech of comparable quality with only 0.4M parameters, in contrast to the 9M parameters required by the SOTA.

Robin Netzorg, Alyssa Cote, Sumi Koshin et al.

As experts in voice modification, trans-feminine gender-affirming voice teachers have unique perspectives on voice that confound current understandings of speaker identity. To demonstrate this, we present the Versatile Voice Dataset (VVD), a collection of three speakers modifying their voices along gendered axes. The VVD illustrates that current approaches in speaker modeling, based on categorical notions of gender and a static understanding of vocal texture, fail to account for the flexibility of the vocal tract. Utilizing publicly-available speaker embeddings, we demonstrate that gender classification systems are highly sensitive to voice modification, and speaker verification systems fail to identify voices as coming from the same speaker as voice modification becomes more drastic. As one path towards moving beyond categorical and static notions of speaker identity, we propose modeling individual qualities of vocal texture such as pitch, resonance, and weight.

Gašper Beguš, Thomas Lu, Alan Zhou et al.

Humans encode information into sounds by controlling articulators and decode information from sounds using the auditory apparatus. This paper introduces CiwaGAN, a model of human spoken language acquisition that combines unsupervised articulatory modeling with an unsupervised model of information exchange through the auditory modality. While prior research includes unsupervised articulatory modeling and information exchange separately, our model is the first to combine the two components. The paper also proposes an improved articulatory model with more interpretable internal representations. The proposed CiwaGAN model is the most realistic approximation of human spoken language acquisition using deep learning. As such, it is useful for cognitively plausible simulations of the human speech act.

Lutfi Eren Erdogan, Nicholas Lee, Sehoon Kim et al.

Large language models (LLMs) have shown remarkable advancements in enabling language agents to tackle simple tasks. However, applying them for complex, multi-step, long-horizon tasks remains a challenge. Recent work have found success by separating high-level planning from low-level execution, which enables the model to effectively balance high-level planning objectives and low-level execution details. However, generating accurate plans remains difficult since LLMs are not inherently trained for this task. To address this, we propose Plan-and-Act, a novel framework that incorporates explicit planning into LLM-based agents and introduces a scalable method to enhance plan generation through a novel synthetic data generation method. Plan-and-Act consists of a Planner model which generates structured, high-level plans to achieve user goals, and an Executor model that translates these plans into environment-specific actions. To train the Planner effectively, we introduce a synthetic data generation method that annotates ground-truth trajectories with feasible plans, augmented with diverse and extensive examples to enhance generalization. We evaluate Plan-and-Act using web navigation as a representative long-horizon planning environment, demonstrating a state-of-the-art 57.58% success rate on the WebArena-Lite benchmark as well as a text-only state-of-the-art 81.36% success rate on WebVoyager.

Guan-Ting Lin, Jiachen Lian, Tingle Li et al.

Spoken dialogue modeling poses challenges beyond text-based language modeling, requiring real-time interaction, turn-taking, and backchanneling. While most Spoken Dialogue Models (SDMs) operate in half-duplex mode-processing one turn at a time - emerging full-duplex SDMs can listen and speak simultaneously, enabling more natural conversations. However, current evaluations remain limited, focusing mainly on turn-based metrics or coarse corpus-level analyses. To address this, we introduce Full-Duplex-Bench, a benchmark that systematically evaluates key interactive behaviors: pause handling, backchanneling, turn-taking, and interruption management. Our framework uses automatic metrics for consistent, reproducible assessment and provides a fair, fast evaluation setup. By releasing our benchmark and code, we aim to advance spoken dialogue modeling and foster the development of more natural and engaging SDMs.

Robin Netzorg, Ajil Jalal, Luna McNulty et al.

Perceptual modification of voice is an elusive goal. While non-experts can modify an image or sentence perceptually with available tools, it is not clear how to similarly modify speech along perceptual axes. Voice conversion does make it possible to convert one voice to another, but these modifications are handled by black box models, and the specifics of what perceptual qualities to modify and how to modify them are unclear. Towards allowing greater perceptual control over voice, we introduce PerMod, a conditional latent diffusion model that takes in an input voice and a perceptual qualities vector, and produces a voice with the matching perceptual qualities. Unlike prior work, PerMod generates a new voice corresponding to specific perceptual modifications. Evaluating perceptual quality vectors with RMSE from both human and predicted labels, we demonstrate that PerMod produces voices with the desired perceptual qualities for typical voices, but performs poorly on atypical voices.

Cheol Jun Cho, Peter Wu, Tejas S. Prabhune et al.

Vocal tract articulation is a natural, grounded control space of speech production. The spatiotemporal coordination of articulators combined with the vocal source shapes intelligible speech sounds to enable effective spoken communication. Based on this physiological grounding of speech, we propose a new framework of neural encoding-decoding of speech -- Speech Articulatory Coding (SPARC). SPARC comprises an articulatory analysis model that infers articulatory features from speech audio, and an articulatory synthesis model that synthesizes speech audio from articulatory features. The articulatory features are kinematic traces of vocal tract articulators and source features, which are intuitively interpretable and controllable, being the actual physical interface of speech production. An additional speaker identity encoder is jointly trained with the articulatory synthesizer to inform the voice texture of individual speakers. By training on large-scale speech data, we achieve a fully intelligible, high-quality articulatory synthesizer that generalizes to unseen speakers. Furthermore, the speaker embedding is effectively disentangled from articulations, which enables accent-perserving zero-shot voice conversion. To the best of our knowledge, this is the first demonstration of universal, high-performance articulatory inference and synthesis, suggesting the proposed framework as a powerful coding system of speech.

Pengfei Sun, Gopala K. Anumanchipalli, Edward F. Chang

Decoding language representations directly from the brain can enable new Brain-Computer Interfaces (BCI) for high bandwidth human-human and human-machine communication. Clinically, such technologies can restore communication in people with neurological conditions affecting their ability to speak. In this study, we propose a novel deep network architecture Brain2Char, for directly decoding text (specifically character sequences) from direct brain recordings (called Electrocorticography, ECoG). Brain2Char framework combines state-of-the-art deep learning modules --- 3D Inception layers for multiband spatiotemporal feature extraction from neural data and bidirectional recurrent layers, dilated convolution layers followed by language model weighted beam search to decode character sequences, optimizing a connectionist temporal classification (CTC) loss. Additionally, given the highly non-linear transformations that underlie the conversion of cortical function to character sequences, we perform regularizations on the network's latent representations motivated by insights into cortical encoding of speech production and artifactual aspects specific to ECoG data acquisition. To do this, we impose auxiliary losses on latent representations for articulatory movements, speech acoustics and session specific non-linearities. In 3 participants tested here, Brain2Char achieves 10.6\%, 8.5\% and 7.0\% Word Error Rates (WER) respectively on vocabulary sizes ranging from 1200 to 1900 words. Brain2Char also performs well when 2 participants silently mimed sentences. These results set a new state-of-the-art on decoding text from brain and demonstrate the potential of Brain2Char as a high-performance communication BCI.