ICLR 2025 Papers

We introduce T2V2 (**T**ext to **V**oice and **V**oice to **T**ext), a unified non-autoregressive model capable of performing both automatic speech recognition (ASR) and text-to-speech (TTS) synthesis within the same framework. T2V2 uses a shared Conformer backbone with rotary positional embeddings to efficiently handle these core tasks, with ASR trained using Connectionist Temporal Classification (CTC) loss and TTS using masked language modeling (MLM) loss. The model operates on discrete tokens, where speech tokens are generated by clustering features from a self-supervised learning model. To further enhance performance, we introduce auxiliary tasks: CTC error correction to refine raw ASR outputs using contextual information from speech embeddings, and unconditional speech MLM, enabling classifier free guidance to improve TTS. Our method is self-contained, leveraging intermediate CTC outputs to align text and speech using Monotonic Alignment Search, without relying on external aligners. We perform extensive experimental evaluation to verify the efficacy of the T2V2 framework, achieving state-of-the-art performance on TTS task and competitive performance in discrete ASR.

Current deep neural networks for speech enhancement (SE) aim to minimize the distance between the output signal and the clean target by filtering out noise features from input features. However, when noise and speech components are highly similar, SE models struggle to learn effective discrimination patterns. To address this challenge, we propose a Filter-Recycle-Interguide framework termed Filter-Recycle-INterGuide NETwork (FIRING-Net) for SE, which filters the input features to extract target features and recycles the filtered-out features as non-target features. These two feature sets then guide each other to refine the features, leading to the aggregation of speech information within the target features and noise information within the non-target features. The proposed FIRING-Net mainly consists of a Local Module (LM) and a Global Module (GM). The LM uses outputs of the speech extraction network as target features and the residual between input and output as non-target features. The GM leverages the energy distribution of self-attention map to extract target and non-target features guided by highest and lowest energy regions. Both LM and GM include interaction modules to leverage the two feature sets in an inter-guided manner for collecting speech from non-target features and filtering out noise from target features. Experiments confirm the effectiveness of the Filter-Recycle-Interguide framework, with FIRING-Net achieving a strong balance between SE performance and computational efficiency, surpassing comparable models across various SNR levels and noise environments.

Progress in AI is driven largely by the scale and quality of training data. Despite this, there is a deficit of empirical analysis examining the attributes of well-established datasets beyond text. In this work we conduct the largest and first-of-its-kind longitudinal audit across modalities --- popular text, speech, and video datasets --- from their detailed sourcing trends and use restrictions to their geographical and linguistic representation. Our manual analysis covers nearly 4000 public datasets between 1990-2024, spanning 608 languages, 798 sources, 659 organizations, and 67 countries. We find that multimodal machine learning applications have overwhelmingly turned to web-crawled, synthetic, and social media platforms, such as YouTube, for their training sets, eclipsing all other sources since 2019. Secondly, tracing the chain of dataset derivations we find that while less than 33% of datasets are restrictively licensed, over 80% of the source content in widely-used text, speech, and video datasets, carry non-commercial restrictions. Finally, counter to the rising number of languages and geographies represented in public AI training datasets, our audit demonstrates measures of relative geographical and multilingual representation have failed to significantly improve their coverage since 2013. We believe the breadth of our audit enables us to empirically examine trends in data sourcing, restrictions, and Western-centricity at an ecosystem-level, and that visibility into these questions are essential to progress in responsible AI. As a contribution to ongoing improvements in dataset transparency and responsible use, we release our entire multimodal audit, allowing practitioners to trace data provenance across text, speech, and video.

The recent large-scale text-to-speech (TTS) systems are usually grouped as autoregressive and non-autoregressive systems. The autoregressive systems implicitly model duration but exhibit certain deficiencies in robustness and lack of duration controllability. Non-autoregressive systems require explicit alignment information between text and speech during training and predict durations for linguistic units (e.g. phone), which may compromise their naturalness. In this paper, we introduce $\textbf{Mask}$ed $\textbf{G}$enerative $\textbf{C}$odec $\textbf{T}$ransformer (MaskGCT), a fully non-autoregressive TTS model that eliminates the need for explicit alignment information between text and speech supervision, as well as phone-level duration prediction. MaskGCT is a two-stage model: in the first stage, the model uses text to predict semantic tokens extracted from a speech self-supervised learning (SSL) model, and in the second stage, the model predicts acoustic tokens conditioned on these semantic tokens. MaskGCT follows the mask-and-predict learning paradigm. During training, MaskGCT learns to predict masked semantic or acoustic tokens based on given conditions and prompts. During inference, the model generates tokens of a specified length in a parallel manner. Experiments with 100K hours of in-the-wild speech demonstrate that MaskGCT outperforms the current state-of-the-art zero-shot TTS systems in terms of quality, similarity, and intelligibility. Audio samples are available at https://maskgct.github.io/. We release our code and model checkpoints at https://github.com/open-mmlab/Amphion/blob/main/models/tts/maskgct.

Despite the significant advancements in Text-to-SQL (Text2SQL) facilitated by large language models (LLMs), the latest state-of-the-art techniques are still trapped in the in-context learning of closed-source LLMs (e.g., GPT-4), which limits their applicability in open scenarios. To address this challenge, we propose a novel RObust mUltitask Tuning and collaboration mEthod (ROUTE) to improve the comprehensive capabilities of open-source LLMs for Text2SQL, thereby providing a more practical solution. Our approach begins with multi-task supervised fine-tuning (SFT) using various synthetic training data related to SQL generation. Unlike existing SFT-based Text2SQL methods, we introduced several additional SFT tasks, including schema linking, noise correction, and continuation writing. Engaging in a variety of SQL generation tasks enhances the model's understanding of SQL syntax and improves its ability to generate high-quality SQL queries. Additionally, inspired by the collaborative modes of LLM agents, we introduce a Multitask Collaboration Prompting (MCP) strategy. This strategy leverages collaboration across several SQL-related tasks to reduce hallucinations during SQL generation, thereby maximizing the potential of enhancing Text2SQL performance through explicit multitask capabilities. Extensive experiments and in-depth analyses have been performed on eight open-source LLMs and five widely-used benchmarks. The results demonstrate that our proposal outperforms the latest Text2SQL methods and yields leading performance.

Architectures such as Linformer and Mamba have recently emerged as competitive linear time replacements for transformers. However, corresponding large pretrained models are often unavailable, especially in non-text domains. To remedy this, we present a Cross-Architecture Layerwise Distillation (CALD) approach that jointly converts a transformer model to a linear time substitute and fine-tunes it to a target task. We also compare several means to guide the fine-tuning to optimally retain the desired inference capability from the original model. The methods differ in their use of the target model and the trajectory of the parameters. In a series of empirical studies on language processing, language modeling, and speech processing, we show that CALD can effectively recover the result of the original model, and that the guiding strategy contributes to the result. Some reasons for the variation are suggested.

Recently, Text-to-speech (TTS) models based on large language models (LLMs) that translate natural language text into sequences of discrete audio tokens have gained great research attention, with advances in neural audio codec (NAC) mod- els using residual vector quantization (RVQ). However, long-form speech synthe- sis remains a significant challenge due to the high frame rate, which increases the length of audio tokens and makes it difficult for autoregressive language models to generate audio tokens for even a minute of speech. To address this challenge, this paper introduces two novel post-training approaches: 1) Multi-Resolution Re- quantization (MReQ) and 2) HALL-E. MReQ is a framework to reduce the frame rate of pre-trained NAC models. Specifically, it incorporates multi-resolution residual vector quantization (MRVQ) module that hierarchically reorganizes dis- crete audio tokens through teacher-student distillation. HALL-E is an LLM-based TTS model designed to predict hierarchical tokens of MReQ. Specifically, it incor- porates the technique of using MRVQ sub-modules and continues training from a pre-trained LLM-based TTS model. Furthermore, to promote TTS research, we create MinutesSpeech, a new benchmark dataset consisting of 40k hours of filtered speech data for training and evaluating speech synthesis ranging from 3s up to 180s. In experiments, we demonstrated the effectiveness of our approaches by ap- plying our post-training framework to VALL-E. We achieved the frame rate down to as low as 8 Hz, enabling the stable minitue-long speech synthesis in a single inference step. Audio samples, dataset, codes and pre-trained models are available at https://yutonishimura-v2.github.io/HALL-E_DEMO.

The tokenization of audio with neural audio codec models is a vital part of modern AI pipelines for the generation or understanding of speech, alone or in a multimodal context. Traditionally such tokenization models have concentrated on low parameter-count architectures using only components with strong inductive biases. In this work we show that by applying a transformer architecture with large parameter count to this problem, and applying a flexible Finite Scalar Quantization (FSQ) based bottleneck, it is possible to reach state-of-the-art speech quality at extremely low bit-rates of $400$ or $700$ bits-per-second. The trained models strongly out-perform existing baselines in both objective and subjective tests.

Speech language models (SpeechLMs) accept speech input and produce speech output, allowing for more natural human-computer interaction compared to text-based large language models (LLMs). Traditional approaches for developing SpeechLMs are constrained by the limited availability of unsupervised speech data and parallel speech-text data, which are significantly less abundant compared to text pre-training data, thereby limiting their scalability as LLMs. We propose a novel approach to scaling speech-text pre-training by leveraging large-scale synthetic interleaved data derived from text corpora, eliminating the need for parallel speech-text datasets. Our method efficiently constructs speech-text interleaved data by sampling text spans from existing text corpora and synthesizing corresponding speech spans using a text-to-token model, bypassing the need to generate actual speech. We also employ a supervised speech tokenizer derived from an automatic speech recognition (ASR) model by incorporating a vector-quantized bottleneck into the encoder. This supervised training approach results in discrete speech tokens with strong semantic preservation even at lower sampling rates (e.g. 12.5Hz), while still maintaining speech reconstruction quality. Starting from a pre-trained language model and scaling our pre-training to 1 trillion tokens (with 600B synthetic interleaved speech-text data), we achieve state-of-the-art performance in both speech language modeling and spoken question answering, improving performance on spoken questions tasks from the previous SOTA of 13\% (Moshi) to 31\%. We further demonstrate that by fine-tuning the pre-trained model with speech dialogue data, we can develop an end-to-end spoken chatbot that achieves competitive performance comparable to existing baselines in both conversational abilities and speech quality, even operating exclusively in the speech domain.

Text-to-image (T2I) diffusion models have demonstrated impressive image generation capabilities. Still, their computational intensity prohibits resource-constrained organizations from deploying T2I models after fine-tuning them on their internal *target* data. While pruning techniques offer a potential solution to reduce the computational burden of T2I models, static pruning methods use the same pruned model for all input prompts, overlooking the varying capacity requirements of different prompts. Dynamic pruning addresses this issue by utilizing a separate sub-network for each prompt, but it prevents batch parallelism on GPUs. To overcome these limitations, we introduce Adaptive Prompt-Tailored Pruning (APTP), a novel prompt-based pruning method designed for T2I diffusion models. Central to our approach is a *prompt router* model, which learns to determine the required capacity for an input text prompt and routes it to an architecture code, given a total desired compute budget for prompts. Each architecture code represents a specialized model tailored to the prompts assigned to it, and the number of codes is a hyperparameter. We train the prompt router and architecture codes using contrastive learning, ensuring that similar prompts are mapped to nearby codes. Further, we employ optimal transport to prevent the codes from collapsing into a single one. We demonstrate APTP's effectiveness by pruning Stable Diffusion (SD) V2.1 using CC3M and COCO as *target* datasets. APTP outperforms the single-model pruning baselines in terms of FID, CLIP, and CMMD scores. Our analysis of the clusters learned by APTP reveals they are semantically meaningful. We also show that APTP can automatically discover previously empirically found challenging prompts for SD, *e.g.,* prompts for generating text images, assigning them to higher capacity codes.

The advent of text-to-image generative models has led artists to worry that their individual styles may be copied, creating a pressing need to reconsider the lack of protection for artistic styles under copyright law. This requires answering challenging questions, like what defines style and what constitutes style infringment. In this work, we build on prior legal scholarship to develop an automatic and interpretable framework to \emph{quantitatively} assess style infringement. Our methods hinge on a simple logical argument: if an artist's works can consistently be recognized as their own, then they have a unique style. Based on this argument, we introduce ArtSavant, a practical (i.e., efficient and easy to understand) tool to (i) determine the unique style of an artist by comparing it to a reference corpus of works from hundreds of artists, and (ii) recognize if the identified style reappears in generated images. We then apply ArtSavant in an empirical study to quantify the prevalence of artistic style copying across 3 popular text-to-image generative models, finding that under simple prompting, $20\\%$ of $372$ prolific artists studied appear to have their styles be at risk of copying by today's generative models. Our findings show that prior legal arguments can be operationalized in quantitative ways, towards more nuanced examination of the issue of artistic style infringements.