Search Results for author:
Found 21 papers, 8 papers with code
The Zero Resource Speech Benchmark 2021: Metrics and baselines for unsupervised spoken language modeling
We introduce a new unsupervised task, spoken language modeling: the learning of linguistic representations from raw audio signals without any labels, along with the Zero Resource Speech Benchmark 2021: a suite of 4 black-box, zero-shot metrics probing for the quality of the learned models at 4 linguistic levels: phonetics, lexicon, syntax and semantics.
RNNs implicitly implement tensor-product representations
Recurrent neural networks (RNNs) can learn continuous vector representations of symbolic structures such as sequences and sentences; these representations often exhibit linear regularities (analogies).
Analogies minus analogy test: measuring regularities in word embeddings
Vector space models of words have long been claimed to capture linguistic regularities as simple vector translations, but problems have been raised with this claim.
Paraphrases do not explain word analogies
Many types of distributional word embeddings (weakly) encode linguistic regularities as directions (the difference between "jump" and "jumped" will be in a similar direction to that of "walk" and "walked," and so on).
Perceptimatic: A human speech perception benchmark for unsupervised subword modelling
In this paper, we present a data set and methods to compare speech processing models and human behaviour on a phone discrimination task.
Zero Resource Code-switched Speech Benchmark Using Speech Utterance Pairs For Multiple Spoken Languages
We introduce a new zero resource code-switched speech benchmark designed to directly assess the code-switching capabilities of self-supervised speech encoders.
The Zero Resource Speech Challenge 2017
We describe a new challenge aimed at discovering subword and word units from raw speech.
Learning weakly supervised multimodal phoneme embeddings
Recent works have explored deep architectures for learning multimodal speech representation (e. g. audio and images, articulation and audio) in a supervised way.
RNNs Implicitly Implement Tensor Product Representations
Recurrent neural networks (RNNs) can learn continuous vector representations of symbolic structures such as sequences and sentences; these representations often exhibit linear regularities (analogies).
The Zero Resource Speech Challenge 2019: TTS without T
We present the Zero Resource Speech Challenge 2019, which proposes to build a speech synthesizer without any text or phonetic labels: hence, TTS without T (text-to-speech without text).
The Perceptimatic English Benchmark for Speech Perception Models
We show that DeepSpeech, a standard English speech recognizer, is more specialized on English phoneme discrimination than English listeners, and is poorly correlated with their behaviour, even though it yields a low error on the decision task given to humans.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
The Zero Resource Speech Challenge 2020: Discovering discrete subword and word units
We present the Zero Resource Speech Challenge 2020, which aims at learning speech representations from raw audio signals without any labels.
The Zero Resource Speech Challenge 2021: Spoken language modelling
We present the Zero Resource Speech Challenge 2021, which asks participants to learn a language model directly from audio, without any text or labels.
Predicting non-native speech perception using the Perceptual Assimilation Model and state-of-the-art acoustic models
Our native language influences the way we perceive speech sounds, affecting our ability to discriminate non-native sounds.
Do self-supervised speech models develop human-like perception biases?
We show that the CPC model shows a small native language effect, but that wav2vec 2. 0 and HuBERT seem to develop a universal speech perception space which is not language specific.
Toward a realistic model of speech processing in the brain with self-supervised learning
These elements, resulting from the largest neuroimaging benchmark to date, show how self-supervised learning can account for a rich organization of speech processing in the brain, and thus delineate a path to identify the laws of language acquisition which shape the human brain.
Are word boundaries useful for unsupervised language learning?
However, word boundary information may be absent or unreliable in the case of speech input (word boundaries are not marked explicitly in the speech stream).
Evaluating context-invariance in unsupervised speech representations
Unsupervised speech representations have taken off, with benchmarks (SUPERB, ZeroSpeech) demonstrating major progress on semi-supervised speech recognition, speech synthesis, and speech-only language modelling.
Self-supervised language learning from raw audio: Lessons from the Zero Resource Speech Challenge
Recent progress in self-supervised or unsupervised machine learning has opened the possibility of building a full speech processing system from raw audio without using any textual representations or expert labels such as phonemes, dictionaries or parse trees.
Bigger is not Always Better: The Effect of Context Size on Speech Pre-Training
It has been generally assumed in the automatic speech recognition (ASR) literature that it is better for models to have access to wider context windows.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
