相关论文: Do Self-Supervised Speech Models Exhibit the Criti…

This study investigates how learners organize perceptual space in early phonetic acquisition by advancing previous studies in two key aspects. Firstly, it examines the shape of the learned hidden representation as well as its ability to…

Large language models accumulate vast knowledge during pre-training, yet the dynamics governing this acquisition remain poorly understood. This work investigates the learning dynamics of language models on a synthetic factual recall task,…

Human reading behavior is tuned to the statistics of natural language: the time it takes human subjects to read a word can be predicted from estimates of the word's probability in context. However, it remains an open question what…

Neural language models (LMs) are arguably less data-efficient than humans from a language acquisition perspective. One fundamental question is why this human-LM gap arises. This study explores the advantage of grounded language acquisition,…

Memory, a fundamental component of human cognition, exhibits adaptive yet fallible characteristics as illustrated by Schacter's memory "sins".These cognitive phenomena have been studied extensively in psychology and neuroscience, but the…

Utilizing Self-Supervised Learning (SSL) models for Speech Emotion Recognition (SER) has proven effective, yet limited research has explored cross-lingual scenarios. This study presents a comparative analysis between human performance and…

Speech models have gained traction thanks to increase in accuracy from novel transformer architectures. While this impressive increase in performance across automatic speech recognition (ASR) benchmarks is noteworthy, there is still much…

Humans acquire language through implicit learning, absorbing complex patterns without explicit awareness. While LLMs demonstrate impressive linguistic capabilities, it remains unclear whether they exhibit human-like pattern recognition…

Understanding how infants perceive speech sounds and language structures is still an open problem. Previous research in artificial neural networks has mainly focused on large dataset-dependent generative models, aiming to replicate…

The identity of a speaker influences language comprehension through modulating perception and expectation. This review explores speaker effects and proposes an integrative model of language and speaker processing that integrates distinct…

Speech Language Models (SLMs) aim to learn language from raw audio, without textual resources. Despite significant advances, our current models exhibit weak syntax and semantic abilities. However, if the scaling properties of neural…

While current large language models have achieved a remarkable success, their data efficiency remains a challenge to overcome. Recently it has been suggested that child-directed speech (CDS) can improve training data efficiency of modern…

Children efficiently acquire language not just by listening, but by interacting with others in their social environment. Conversely, large language models are typically trained with next-word prediction on massive amounts of text. Motivated…

We study word learning in subword and character language models with the psycholinguistic lexical decision task. While subword LMs struggle to discern words and non-words with high accuracy, character LMs solve this task easily and…

This study investigates the extent to which Mel-Frequency Cepstral Coefficients (MFCCs) capture first language (L1) transfer in extended second language (L2) English speech. Speech samples from Mandarin and American English L1 speakers were…

Children's speech recognition is a vital, yet largely overlooked domain when building inclusive speech technologies. The major challenge impeding progress in this domain is the lack of adequate child speech corpora; however, recent advances…

Self-supervised representation learning (SSRL) has demonstrated superior performance than supervised models for tasks including phoneme recognition. Training SSRL models poses a challenge for low-resource languages where sufficient…

While discrete latent variable models have had great success in self-supervised learning, most models assume that frames are independent. Due to the segmental nature of phonemes in speech perception, modeling dependencies among latent…

This work explores the degree to which grammar acquisition is driven by language `simplicity' and the source modality (speech vs. text) of data. Using BabyBERTa as a probe, we find that grammar acquisition is largely driven by exposure to…

Contrastive language-audio pre-training (CLAP), which learns audio-language representations by aligning audio and text in a common feature space, has become popular for solving audio tasks. However, CLAP's audio features lack…