Search Results for author:
Found 41 papers, 15 papers with code
HashCount at SemEval-2018 Task 3: Concatenative Featurization of Tweet and Hashtags for Irony Detection
This paper proposes a novel feature extraction process for SemEval task 3: Irony detection in English tweets.
Extracting Arguments from Korean Question and Command: An Annotated Corpus for Structured Paraphrasing
Intention identification is a core issue in dialog management.
Giving Space to Your Message: Assistive Word Segmentation for the Electronic Typing of Digital Minorities
For readability and disambiguation of the written text, appropriate word segmentation is recommended for documentation, and it also holds for the digitized texts.
Speech Intention Understanding in a Head-final Language: A Disambiguation Utilizing Intonation-dependency
This paper suggests a system which identifies the inherent intention of a spoken utterance given its transcript, in some cases using auxiliary acoustic features.
On Measuring Gender Bias in Translation of Gender-neutral Pronouns
However, detection and evaluation of gender bias in the machine translation systems are not yet thoroughly investigated, for the task being cross-lingual and challenging to define.
Investigating an Effective Character-level Embedding in Korean Sentence Classification
Different from the writing systems of many Romance and Germanic languages, some languages or language families show complex conjunct forms in character composition.
Text Matters but Speech Influences: A Computational Analysis of Syntactic Ambiguity Resolution
Analyzing how human beings resolve syntactic ambiguity has long been an issue of interest in the field of linguistics.
Machines Getting with the Program: Understanding Intent Arguments of Non-Canonical Directives
Modern dialog managers face the challenge of having to fulfill human-level conversational skills as part of common user expectations, including but not limited to discourse with no clear objective.
Discourse Component to Sentence (DC2S): An Efficient Human-Aided Construction of Paraphrase and Sentence Similarity Dataset
Assessing the similarity of sentences and detecting paraphrases is an essential task both in theory and practice, but achieving a reliable dataset requires high resource.
Towards an Efficient Code-Mixed Grapheme-to-Phoneme Conversion in an Agglutinative Language: A Case Study on To-Korean Transliteration
Code-mixed grapheme-to-phoneme (G2P) conversion is a crucial issue for modern speech recognition and synthesis task, but has been seldom investigated in sentence-level in literature.
Speech to Text Adaptation: Towards an Efficient Cross-Modal Distillation
We transfer the knowledge from a concrete Transformer-based text LM to an SLU module which can face a data shortage, based on recent cross-modal distillation methodologies.
WaveNODE: A Continuous Normalizing Flow for Speech Synthesis
In recent years, various flow-based generative models have been proposed to generate high-fidelity waveforms in real-time.
SoftFlow: Probabilistic Framework for Normalizing Flow on Manifolds
Flow-based generative models are composed of invertible transformations between two random variables of the same dimension.
Ranked #3 on
Point Cloud Generation
on ShapeNet Airplane
TutorNet: Towards Flexible Knowledge Distillation for End-to-End Speech Recognition
To reduce this computational burden, knowledge distillation (KD), which is a popular model compression method, has been used to transfer knowledge from a deep and complex model (teacher) to a shallower and simpler model (student).
Robust Text-Dependent Speaker Verification via Character-Level Information Preservation for the SdSV Challenge 2020
This paper describes our submission to Task 1 of the Short-duration Speaker Verification (SdSV) challenge 2020.
Audio and Speech Processing Sound
Unsupervised Representation Learning for Speaker Recognition via Contrastive Equilibrium Learning
In this paper, we propose a simple but powerful unsupervised learning method for speaker recognition, namely Contrastive Equilibrium Learning (CEL), which increases the uncertainty on nuisance factors latent in the embeddings by employing the uniformity loss.
Continuous Monitoring of Blood Pressure with Evidential Regression
Photoplethysmogram (PPG) signal-based blood pressure (BP) estimation is a promising candidate for modern BP measurements, as PPG signals can be easily obtained from wearable devices in a non-invasive manner, allowing quick BP measurement.
StyleKQC: A Style-Variant Paraphrase Corpus for Korean Questions and Commands
Paraphrasing is often performed with less concern for controlled style conversion.
Expressive Text-to-Speech using Style Tag
In this work, we propose StyleTagging-TTS (ST-TTS), a novel expressive TTS model that utilizes a style tag written in natural language.
Diff-TTS: A Denoising Diffusion Model for Text-to-Speech
Although neural text-to-speech (TTS) models have attracted a lot of attention and succeeded in generating human-like speech, there is still room for improvements to its naturalness and architectural efficiency.
Kosp2e: Korean Speech to English Translation Corpus
Most speech-to-text (S2T) translation studies use English speech as a source, which makes it difficult for non-English speakers to take advantage of the S2T technologies.
Oracle Teacher: Leveraging Target Information for Better Knowledge Distillation of CTC Models
Extending this supervised scheme further, we introduce a new type of teacher model for connectionist temporal classification (CTC)-based sequence models, namely Oracle Teacher, that leverages both the source inputs and the output labels as the teacher model's input.
Bootstrap Equilibrium and Probabilistic Speaker Representation Learning for Self-supervised Speaker Verification
In this paper, we propose self-supervised speaker representation learning strategies, which comprise of a bootstrap equilibrium speaker representation learning in the front-end and an uncertainty-aware probabilistic speaker embedding training in the back-end.
Transfer Learning Framework for Low-Resource Text-to-Speech using a Large-Scale Unlabeled Speech Corpus
The experimental results verify the effectiveness of the proposed method in terms of naturalness, intelligibility, and speaker generalization.
Frequency and Multi-Scale Selective Kernel Attention for Speaker Verification
The SKA mechanism allows each convolutional layer to adaptively select the kernel size in a data-driven fashion.
HuBERT-EE: Early Exiting HuBERT for Efficient Speech Recognition
Pre-training with self-supervised models, such as Hidden-unit BERT (HuBERT) and wav2vec 2. 0, has brought significant improvements in automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Disentangled Speaker Representation Learning via Mutual Information Minimization
The experimental results show that fine-tuning with a disentanglement framework on a existing pre-trained model is valid and can further improve performance.
Fully Unsupervised Training of Few-shot Keyword Spotting
For training a few-shot keyword spotting (FS-KWS) model, a large labeled dataset containing massive target keywords has known to be essential to generalize to arbitrary target keywords with only a few enrollment samples.
Adversarial Speaker-Consistency Learning Using Untranscribed Speech Data for Zero-Shot Multi-Speaker Text-to-Speech
Several recently proposed text-to-speech (TTS) models achieved to generate the speech samples with the human-level quality in the single-speaker and multi-speaker TTS scenarios with a set of pre-defined speakers.
Inter-KD: Intermediate Knowledge Distillation for CTC-Based Automatic Speech Recognition
Recently, the advance in deep learning has brought a considerable improvement in the end-to-end speech recognition field, simplifying the traditional pipeline while producing promising results.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
SNAC: Speaker-normalized affine coupling layer in flow-based architecture for zero-shot multi-speaker text-to-speech
Zero-shot multi-speaker text-to-speech (ZSM-TTS) models aim to generate a speech sample with the voice characteristic of an unseen speaker.
When Crowd Meets Persona: Creating a Large-Scale Open-Domain Persona Dialogue Corpus
Building a natural language dataset requires caution since word semantics is vulnerable to subtle text change or the definition of the annotated concept.
Towards single integrated spoofing-aware speaker verification embeddings
Second, competitive performance should be demonstrated compared to the fusion of automatic speaker verification (ASV) and countermeasure (CM) embeddings, which outperformed single embedding solutions by a large margin in the SASV2022 challenge.
MCR-Data2vec 2.0: Improving Self-supervised Speech Pre-training via Model-level Consistency Regularization
Self-supervised learning (SSL) has shown significant progress in speech processing tasks.
EM-Network: Oracle Guided Self-distillation for Sequence Learning
We introduce EM-Network, a novel self-distillation approach that effectively leverages target information for supervised sequence-to-sequence (seq2seq) learning.
Transduce and Speak: Neural Transducer for Text-to-Speech with Semantic Token Prediction
We introduce a text-to-speech(TTS) framework based on a neural transducer.
EEND-DEMUX: End-to-End Neural Speaker Diarization via Demultiplexed Speaker Embeddings
In recent years, there have been studies to further improve the end-to-end neural speaker diarization (EEND) systems.
Efficient Parallel Audio Generation using Group Masked Language Modeling
We present a fast and high-quality codec language model for parallel audio generation.
Utilizing Neural Transducers for Two-Stage Text-to-Speech via Semantic Token Prediction
We also delve into the inference speed and prosody control capabilities of our approach, highlighting the potential of neural transducers in TTS frameworks.
OpenKorPOS: Democratizing Korean Tokenization with Voting-Based Open Corpus Annotation
As this problem originates from the conventional scheme used when creating a POS tagging corpus, we propose an improvement to the existing scheme, which makes it friendlier to generative tasks.
