相关论文: SGPA: Spectrogram-Guided Phonetic Alignment for Fe…

Pooling is needed to aggregate frame-level features into utterance-level representations for speaker modeling. Given the success of statistics-based pooling methods, we hypothesize that speaker characteristics are well represented in the…

Recent advancements in retrieval-augmented generation (RAG) have enhanced large language models in question answering by integrating external knowledge. However, challenges persist in achieving global understanding and aligning responses…

Speech enhancement models have greatly progressed in recent years, but still show limits in perceptual quality of their speech outputs. We propose an objective for perceptual quality based on temporal acoustic parameters. These are…

Computing the agreement between two continuous sequences is of great interest in statistics when comparing two instruments or one instrument with a gold standard. The probability of agreement (PA) quantifies the similarity between two…

High-fidelity text-to-music generation typically relies on massive proprietary datasets and immense computational resources. Existing models often struggle to generate coherent pure musical accompaniments and lack precise, localized…

In modern LLMs, linguistic features function not as stylistic artifacts but as probes of probability mass, allocated under training alignment objectives. Language models trained with contemporary pipelines exhibit severe reshaping of…

Some recent studies have demonstrated the feasibility of single-stage neural text-to-speech, which does not need to generate mel-spectrograms but generates the raw waveforms directly from the text. Single-stage text-to-speech often faces…

The advancement of large language models (LLMs) is critically dependent on the availability of high-quality datasets for Supervised Fine-Tuning (SFT), alignment tasks like Direct Preference Optimization (DPO), etc. In this work, we present…

Recognition of speech, and in particular the ability to generalize and learn from small sets of labelled examples like humans do, depends on an appropriate representation of the acoustic input. We formulate the problem of finding robust…

Score-based generative models (SGMs) have recently shown impressive results for difficult generative tasks such as the unconditional and conditional generation of natural images and audio signals. In this work, we extend these models to the…

While attribution methods, such as Shapley values, are widely used to explain the importance of features or training data in traditional machine learning, their application to Large Language Models (LLMs), particularly within…

The increasing complexity of foundational models underscores the necessity for explainability, particularly for fine-tuning, the most widely used training method for adapting models to downstream tasks. Instance attribution, one type of…

Multilingual transformer-based models demonstrate remarkable zero and few-shot transfer across languages by learning and reusing language-agnostic features. However, as a fixed-size model acquires more languages, its performance across all…

Grapheme-to-phoneme conversion (g2p) is necessary for text-to-speech and automatic speech recognition systems. Most g2p systems are monolingual: they require language-specific data or handcrafting of rules. Such systems are difficult to…

We propose a multi-dimensional structured state space (S4) approach to speech enhancement. To better capture the spectral dependencies across the frequency axis, we focus on modifying the multi-dimensional S4 layer with whitening…

We propose WHISPER-GPT: A generative large language model (LLM) for speech and music that allows us to work with continuous audio representations and discrete tokens simultaneously as part of a single architecture. There has been a huge…

Data is a critical asset for training large language models (LLMs), alongside compute resources and skilled workers. While some training data is publicly available, substantial investment is required to generate proprietary datasets, such…

One of the most important parts of an end-to-end speaker verification system is the speaker embedding generation. In our previous paper, we reported that shortcut connections-based multi-layer aggregation improves the representational power…

Despite its widespread adoption as the prominent neural architecture, the Transformer has spurred several independent lines of work to address its limitations. One such approach is selective state space models, which have demonstrated…

Most spoken language translation systems developed to date rely on a pipelined architecture, in which the main stages are speech recognition, linguistic analysis, transfer, generation and speech synthesis. When making projections of error…