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

Child-directed speech (CDS) is a particular type of speech that adults use when addressing young children. Its properties also change as a function of extralinguistic factors, such as age of the child being addressed. Access to large…

Contrastive language-audio pretraining (CLAP) is widely used for audio generation and recognition tasks. For example, CLAPScore, which utilizes the similarity of CLAP embeddings, has been a major metric for the evaluation of the relevance…

Speech communication systems based on Voice-over-IP technology are frequently used by native as well as non-native speakers of a target language, e.g. in international phone calls or telemeetings. Frequently, such calls also occur in a…

To mitigate the problem of having to traverse over the full vocabulary in the softmax normalization of a neural language model, sampling-based training criteria are proposed and investigated in the context of large vocabulary word-based…

Language Models (LMs) are prone to memorizing parts of their data during training and unintentionally emitting them at generation time, raising concerns about privacy leakage and disclosure of intellectual property. While previous research…

This thesis presents a computational theory of unsupervised language acquisition, precisely defining procedures for learning language from ordinary spoken or written utterances, with no explicit help from a teacher. The theory is based…

Non-native speakers show difficulties with spoken word processing. Many studies attribute these difficulties to imprecise phonological encoding of words in the lexical memory. We test an alternative hypothesis: that some of these…

Self-supervised learning (SSL) has proven vital in speech and audio-related applications. The paradigm trains a general model on unlabeled data that can later be used to solve specific downstream tasks. This type of model is costly to train…

Large language models (LLMs) learn non-trivial abstractions during pretraining, such as detecting irregular plural noun subjects. However, because traditional evaluation methods (e.g., benchmarking) fail to reveal how models acquire these…

Decades of research has studied how language learning infants learn to discriminate speech sounds, segment words, and associate words with their meanings. While gradual development of such capabilities is unquestionable, the exact nature of…

The effects of language mismatch impact speech anti-spoofing systems, while investigations and quantification of these effects remain limited. Existing anti-spoofing datasets are mainly in English, and the high cost of acquiring…

The transition of Large Language Models (LLMs) from exploratory tools to active "silicon subjects" in social science lacks extensive validation of operational validity. This study introduces Conditioned Comment Prediction (CCP), a task in…

Grammatical features across human languages show intriguing correlations often attributed to learning biases in humans. However, empirical evidence has been limited to experiments with highly simplified artificial languages, and whether…

Two of the central factors believed to underpin human sentence processing difficulty are expectations and retrieval from working memory. A recent attempt to create a unified cognitive model integrating these two factors relied on the…

Current conversational agents (CA) have seen improvement in conversational quality in recent years due to the influence of large language models (LLMs) like GPT3. However, two key categories of problem remain. Firstly there are the unique…

Large Language Models (LLM) are already widely used to generate content for a variety of online platforms. As we are not able to safely distinguish LLM-generated content from human-produced content, LLM-generated content is used to train…

Mental manipulation, the strategic use of language to covertly influence or exploit others, is a newly emerging task in computational social reasoning. Prior work has focused exclusively on textual conversations, overlooking how…

Large Language Models (LLMs) can generate text by transferring style attributes like formality resulting in formal or informal text. However, instructing LLMs to generate text that when spoken, is more intelligible in an acoustically…

In this paper we study word stress representations learned by self-supervised speech models (S3M), specifically the Wav2vec 2.0 model. We investigate the S3M representations of word stress for five different languages: Three languages with…

The training of modern large language models (LLMs) takes place in a regime where most training examples are seen only a few times by the model during the course of training. What does a model remember about such examples seen only a few…