Related papers: Boosting Code-Switching ASR with Mixture of Expert…
Recently, Mixture of Experts (MoE) based Transformer has shown promising results in many domains. This is largely due to the following advantages of this architecture: firstly, MoE based Transformer can increase model capacity without…
In this paper, we particularly work on the code-switched text, one of the most common occurrences in the bilingual communities across the world. Due to the discrepancies in the extraction of code-switched text from an Automated Speech…
India is home to multiple languages, and training automatic speech recognition (ASR) systems for languages is challenging. Over time, each language has adopted words from other languages, such as English, leading to code-mixing. Most Indian…
Code understanding is a foundational capability in software engineering tools and developer workflows. However, most existing systems are designed for English-speaking users interacting via keyboards, which limits accessibility in…
While end-to-end Automatic Speech Recognition (ASR) models have shown impressive performance in transcribing general speech, they often struggle to accurately recognize contextually relevant keywords, such as proper nouns or user-specific…
The integration of pre-trained text-based large language models (LLM) with speech input has enabled instruction-following capabilities for diverse speech tasks. This integration requires the use of a speech encoder, a speech adapter, and an…
In-context learning (ICL) facilitates Large Language Models (LLMs) exhibiting emergent ability on downstream tasks without updating billions of parameters. However, in the area of multi-modal Large Language Models (MLLMs), two problems…
Large Language Models (LLMs) have impressive multilingual capabilities, but they suffer from unexpected code-switching, also known as language mixing, which involves switching to unexpected languages in the model response. This problem…
Spoken conversational agents are converging toward voice-native LLMs. This tutorial distills the path from cascaded ASR/NLU to end-to-end, retrieval-and vision-grounded systems. We frame adaptation of text LLMs to audio, cross-modal…
With the widespread adoption of Large Language Models (LLMs), many deep learning practitioners are looking for strategies of running these models more efficiently. One such strategy is to use sparse Mixture-of-Experts (MoE) - a type of…
The Mixtures-of-Experts (MoE) model is a widespread distributed and integrated learning method for large language models (LLM), which is favored due to its ability to sparsify and expand models efficiently. However, the performance of MoE…
The integration of Language Models (LMs) has proven to be an effective way to address domain shifts in speech recognition. However, these approaches usually require a significant amount of target domain text data for the training of LMs.…
We introduce Spirit LM, a foundation multimodal language model that freely mixes text and speech. Our model is based on a 7B pretrained text language model that we extend to the speech modality by continuously training it on text and speech…
This paper presents a novel deep learning architecture for acoustic model in the context of Automatic Speech Recognition (ASR), termed as MixNet. Besides the conventional layers, such as fully connected layers in DNN-HMM and memory cells in…
Scaling distributed training of Large Language Models (LLMs) requires not only algorithmic advances but also efficient utilization of heterogeneous hardware resources. While existing methods such as DiLoCo have demonstrated promising…
Large Language Models (LLMs) have recently garnered significant attention, primarily for their capabilities in text-based interactions. However, natural human interaction often relies on speech, necessitating a shift towards voice-based…
Large Language Models (LLMs) struggle to handle long input sequences due to high memory and runtime costs. Memory-augmented models have emerged as a promising solution to this problem, but current methods are hindered by limited memory…
We focus on the problem of language modeling for code-switched language, in the context of automatic speech recognition (ASR). Language modeling for code-switched language is challenging for (at least) three reasons: (1) lack of available…
While Low-Rank Adaptation (LoRA) enables parameter-efficient fine-tuning for Large Language Models (LLMs), its performance often falls short of Full Fine-Tuning (Full FT). Current methods optimize LoRA by initializing with static singular…
Multimodal large language models (MLLMs) have demonstrated impressive capabilities across various vision-language tasks. However, a generalist MLLM typically underperforms compared with a specialist MLLM on most VL tasks, which can be…