Searcharxiv⌕ Search

arXiv subjects

Nam Soo Kim

Publications and source records attributed to Nam Soo Kim.

At least 19 recordsLinked to original sources
arXiv2026

MD-ProTector: Positioning Multiple Data-Driven Prototypes for LLM-Generated Text Detection

As LLM-generated content becomes more sophisticated, detection systems for distinguishing those texts from human-written text must operate at scale while handling diverse writing styles, domains, languages, and generator models. Input-only encoder detectors are suitable for practical deployment setting, but standard binary classification supplies only the class label and does not explicitly organize the substantial variation within either class. We propose MD-ProTector, which represents each class with multiple trainable reference vectors in the encoder embedding space, referred to as prototypes. These prototypes provide separate decision boundaries for different groups of texts within the same class. However, adding multiple prototypes alone does not determine which variation each prototype should represent. MD-ProTector addresses this problem with Prototype Positioning loss, which separates class-level structure from the within-class variation that differentiates individual prototypes. Evaluated across five settings from three large-scale benchmarks covering domain, generator, language, and adversarial variation, MD-ProTector achieves the highest AvgRec on MAGE CDCM and RAID and the highest AUROC and lowest FPR95 on RAID among the compared encoder-based methods.

cs.CL↗
arXiv2026

ZipL-Dialog: Memory-Efficient Long-Form Spoken Dialog Synthesis via Latent Flow Matching

Zero-shot dialog TTS benefits from flow-matching, but minute-scale generation on dense mel-spectrograms causes severe memory bottlenecks, often forcing unnatural chunked synthesis. We propose ZipL-Dialog, which shifts conditional flow-matching into a 4x time-compressed (25 Hz) latent space. To preserve acoustic fidelity under compression, we employ a deterministic mel autoencoder with auxiliary mel-domain supervision and optimize the ZipFormer's hierarchical downsampling schedule. Experiments show that ZipL-Dialog reduces maximum peak GPU memory by 11.22x and accelerates inference by 2.23x over the baseline, substantially lowering the memory footprint of single-pass multi-minute dialog synthesis while maintaining perceptual naturalness.

eess.AS↗
arXiv2026

Raon-OpenTTS: Open Models and Data for Robust Text-to-Speech

Recent advances in text-to-speech (TTS) models show impressive speech naturalness and quality, yet the role of large-scale open data in driving this progress remains underexplored. In this work, we introduce Raon-OpenTTS, an open TTS model that performs competitively with state-of-the-art closed-data TTS models, and Raon-OpenTTS-Pool, a large-scale open dataset for reproducible TTS training. Raon-OpenTTS-Pool consists of 615K hours of 240M speech segments aggregated from publicly available English speech corpora and web-sourced recordings. With a model-based filtering pipeline applied to Raon-OpenTTS-Pool, we derive Raon-OpenTTS-Core, a curated, high-quality subset of 510K hours and 194M speech segments. Using Raon-OpenTTS-Core, we train Raon-OpenTTS, a series of diffusion transformer (DiT)-based TTS models from 0.3B to 1B parameters. On multiple benchmarks, Raon-OpenTTS-1B shows comparable performance to state-of-the-art models such as Qwen3-TTS and CosyVoice 3, which are trained on several million hours of proprietary speech data. Notably, on Seed-TTS-Eval, Raon-OpenTTS-1B achieves a word error rate (WER) of 1.78% and a speaker similarity (SIM) of 0.749, ranking second on WER and first on SIM among recent open-weight TTS baselines. On CV3-Hard-EN, Raon-OpenTTS-1B achieves a WER of 6.15% and a SIM of 0.775, ranking first on both metrics. Furthermore, to support robust evaluation, we introduce Raon-OpenTTS-Eval, a structured benchmark for assessing TTS robustness across diverse acoustic conditions including clean, noisy, in-the-wild, and expressive speech. On Raon-OpenTTS-Eval, Raon-OpenTTS-1B achieves the best average WER and SIM among all evaluated models, and the second-best human preference, as measured by comparative mean opinion score (CMOS). Our data pool, filtering pipeline, training code, and checkpoints are publicly available at https://github.com/krafton-ai/RAON-OpenTTS.

eess.AS↗
arXiv2026

SpectCount: Spectrotemporal Counting via Synthetic Signals Improves Large Audio Language Models

Large audio language models (LALMs) extend large language models with an audio encoder and large-scale audio data. However, the scarcity of high-quality annotated audio data remains a fundamental bottleneck for scaling. Through probing signal detectability analysis, we identify fine-grained spectrotemporal perceptual weaknesses in a foundation LALM. To address these challenges, we propose Spectrotemporal Counting (SpectCount), a data-efficient fine-tuning approach based on fully synthetic audio signals generated on-the-fly, without relying on real-world audio, annotations, or pretrained generative models. SpectCount not only resolves the observed weaknesses but also improves performance on diverse auditory benchmarks spanning sound, music, and speech, unseen during fine-tuning. These results suggest that weakness-targeted synthetic signals provide a data-efficient path toward enhanced auditory understanding capabilities in LALMs.

eess.AS↗
arXiv2026

Semantic-Aware Reconstruction Error for Detecting AI-Generated Images

Recently, AI-generated image detection has gained increasing attention, as the rapid advancement of image generation technologies has raised serious concerns about their potential misuse. While existing detection methods have achieved promising results, their performance often degrades significantly when facing fake images from unseen, out-of-distribution (OOD) generative models, since they primarily rely on model-specific artifacts and thus overfit to the models used for training. To address this limitation, we propose a novel representation, namely Semantic-Aware Reconstruction Error (SARE), that measures the semantic difference between an image and its caption-guided reconstruction. The key hypothesis behind SARE is that real images, whose captions often fail to fully capture their complex visual content, may undergo noticeable semantic shifts during the caption-guided reconstruction process. In contrast, fake images, which closely align with their captions, show minimal semantic changes. By quantifying these semantic shifts, SARE provides a robust and discriminative feature for detecting fake images across diverse generative models. Additionally, we introduce a fusion module that integrates SARE into the backbone detector via a cross-attention mechanism. Image features attend to semantic representations extracted from SARE, enabling the model to adaptively leverage semantic information. Experimental results demonstrate that the proposed method achieves strong generalization, outperforming existing baselines on benchmarks including GenImage and ForenSynths. We further validate the effectiveness of caption guidance through a detailed analysis of semantic shifts, confirming its ability to enhance detection robustness.

cs.CV↗
arXiv2025

FastEnhancer: Speed-Optimized Streaming Neural Speech Enhancement

Streaming speech enhancement is a crucial task for real-time applications such as online meetings, smart home appliances, and hearing aids. Deep neural network-based approaches achieve exceptional performance while demanding substantial computational resources. Although recent neural speech enhancement models have succeeded in reducing the number of parameters and multiply-accumulate operations, their sophisticated architectures often introduce significant processing latency on common hardware. In this work, we propose FastEnhancer, a streaming neural speech enhancement model designed explicitly to minimize real-world latency. It features a simple encoder-decoder structure with efficient RNNFormer blocks. Evaluations on various objective metrics show that FastEnhancer achieves state-of-the-art speech quality and intelligibility while simultaneously demonstrating the fastest processing speed on a single CPU thread. Code and pre-trained weights are publicly available (https://github.com/aask1357/fastenhancer).

eess.AS↗
arXiv2025

FADEL: Uncertainty-aware Fake Audio Detection with Evidential Deep Learning

Recently, fake audio detection has gained significant attention, as advancements in speech synthesis and voice conversion have increased the vulnerability of automatic speaker verification (ASV) systems to spoofing attacks. A key challenge in this task is generalizing models to detect unseen, out-of-distribution (OOD) attacks. Although existing approaches have shown promising results, they inherently suffer from overconfidence issues due to the usage of softmax for classification, which can produce unreliable predictions when encountering unpredictable spoofing attempts. To deal with this limitation, we propose a novel framework called fake audio detection with evidential learning (FADEL). By modeling class probabilities with a Dirichlet distribution, FADEL incorporates model uncertainty into its predictions, thereby leading to more robust performance in OOD scenarios. Experimental results on the ASVspoof2019 Logical Access (LA) and ASVspoof2021 LA datasets indicate that the proposed method significantly improves the performance of baseline models. Furthermore, we demonstrate the validity of uncertainty estimation by analyzing a strong correlation between average uncertainty and equal error rate (EER) across different spoofing algorithms.

eess.AS↗
arXiv2024

Towards Maximum Likelihood Training for Transducer-based Streaming Speech Recognition

Transducer neural networks have emerged as the mainstream approach for streaming automatic speech recognition (ASR), offering state-of-the-art performance in balancing accuracy and latency. In the conventional framework, streaming transducer models are trained to maximize the likelihood function based on non-streaming recursion rules. However, this approach leads to a mismatch between training and inference, resulting in the issue of deformed likelihood and consequently suboptimal ASR accuracy. We introduce a mathematical quantification of the gap between the actual likelihood and the deformed likelihood, namely forward variable causal compensation (FoCC). We also present its estimator, FoCCE, as a solution to estimate the exact likelihood. Through experiments on the LibriSpeech dataset, we show that FoCCE training improves the accuracy of the streaming transducers.

eess.AS↗
arXiv2024

SegINR: Segment-wise Implicit Neural Representation for Sequence Alignment in Neural Text-to-Speech

We present SegINR, a novel approach to neural Text-to-Speech (TTS) that addresses sequence alignment without relying on an auxiliary duration predictor and complex autoregressive (AR) or non-autoregressive (NAR) frame-level sequence modeling. SegINR simplifies the process by converting text sequences directly into frame-level features. It leverages an optimal text encoder to extract embeddings, transforming each into a segment of frame-level features using a conditional implicit neural representation (INR). This method, named segment-wise INR (SegINR), models temporal dynamics within each segment and autonomously defines segment boundaries, reducing computational costs. We integrate SegINR into a two-stage TTS framework, using it for semantic token prediction. Our experiments in zero-shot adaptive TTS scenarios demonstrate that SegINR outperforms conventional methods in speech quality with computational efficiency.

eess.AS↗
arXiv2024

HILCodec: High-Fidelity and Lightweight Neural Audio Codec

The recent advancement of end-to-end neural audio codecs enables compressing audio at very low bitrates while reconstructing the output audio with high fidelity. Nonetheless, such improvements often come at the cost of increased model complexity. In this paper, we identify and address the problems of existing neural audio codecs. We show that the performance of the SEANet-based codec does not increase consistently as the network depth increases. We analyze the root cause of such a phenomenon and suggest a variance-constrained design. Also, we reveal various distortions in previous waveform domain discriminators and propose a novel distortion-free discriminator. The resulting model, HILCodec, is a real-time streaming audio codec that demonstrates state-of-the-art quality across various bitrates and audio types.

eess.AS↗
arXiv2024

High Fidelity Text-to-Speech Via Discrete Tokens Using Token Transducer and Group Masked Language Model

We propose a novel two-stage text-to-speech (TTS) framework with two types of discrete tokens, i.e., semantic and acoustic tokens, for high-fidelity speech synthesis. It features two core components: the Interpreting module, which processes text and a speech prompt into semantic tokens focusing on linguistic contents and alignment, and the Speaking module, which captures the timbre of the target voice to generate acoustic tokens from semantic tokens, enriching speech reconstruction. The Interpreting stage employs a transducer for its robustness in aligning text to speech. In contrast, the Speaking stage utilizes a Conformer-based architecture integrated with a Grouped Masked Language Model (G-MLM) to boost computational efficiency. Our experiments verify that this innovative structure surpasses the conventional models in the zero-shot scenario in terms of speech quality and speaker similarity.

eess.AS↗
arXiv2024

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). However, these models usually require an expensive computational cost to achieve outstanding performance, slowing down the inference speed. To improve the model efficiency, we introduce an early exit scheme for ASR, namely HuBERT-EE, that allows the model to stop the inference dynamically. In HuBERT-EE, multiple early exit branches are added at the intermediate layers. When the intermediate prediction of the early exit branch is confident, the model stops the inference, and the corresponding result can be returned early. We investigate the proper early exiting criterion and fine-tuning strategy to effectively perform early exiting. Experimental results on the LibriSpeech show that HuBERT-EE can accelerate the inference of the HuBERT while simultaneously balancing the trade-off between the performance and the latency.

cs.CL↗
arXiv2024

MakeSinger: A Semi-Supervised Training Method for Data-Efficient Singing Voice Synthesis via Classifier-free Diffusion Guidance

In this paper, we propose MakeSinger, a semi-supervised training method for singing voice synthesis (SVS) via classifier-free diffusion guidance. The challenge in SVS lies in the costly process of gathering aligned sets of text, pitch, and audio data. MakeSinger enables the training of the diffusion-based SVS model from any speech and singing voice data regardless of its labeling, thereby enhancing the quality of generated voices with large amount of unlabeled data. At inference, our novel dual guiding mechanism gives text and pitch guidance on the reverse diffusion step by estimating the score of masked input. Experimental results show that the model trained in a semi-supervised manner outperforms other baselines trained only on the labeled data in terms of pronunciation, pitch accuracy and overall quality. Furthermore, we demonstrate that by adding Text-to-Speech (TTS) data in training, the model can synthesize the singing voices of TTS speakers even without their singing voices.

eess.AS↗
arXiv2024

Utilizing Neural Transducers for Two-Stage Text-to-Speech via Semantic Token Prediction

We propose a novel text-to-speech (TTS) framework centered around a neural transducer. Our approach divides the whole TTS pipeline into semantic-level sequence-to-sequence (seq2seq) modeling and fine-grained acoustic modeling stages, utilizing discrete semantic tokens obtained from wav2vec2.0 embeddings. For a robust and efficient alignment modeling, we employ a neural transducer named token transducer for the semantic token prediction, benefiting from its hard monotonic alignment constraints. Subsequently, a non-autoregressive (NAR) speech generator efficiently synthesizes waveforms from these semantic tokens. Additionally, a reference speech controls temporal dynamics and acoustic conditions at each stage. This decoupled framework reduces the training complexity of TTS while allowing each stage to focus on semantic and acoustic modeling. Our experimental results on zero-shot adaptive TTS demonstrate that our model surpasses the baseline in terms of speech quality and speaker similarity, both objectively and subjectively. We also delve into the inference speed and prosody control capabilities of our approach, highlighting the potential of neural transducers in TTS frameworks.

eess.AS↗
arXiv2024

Efficient Parallel Audio Generation using Group Masked Language Modeling

We present a fast and high-quality codec language model for parallel audio generation. While SoundStorm, a state-of-the-art parallel audio generation model, accelerates inference speed compared to autoregressive models, it still suffers from slow inference due to iterative sampling. To resolve this problem, we propose Group-Masked Language Modeling~(G-MLM) and Group Iterative Parallel Decoding~(G-IPD) for efficient parallel audio generation. Both the training and sampling schemes enable the model to synthesize high-quality audio with a small number of iterations by effectively modeling the group-wise conditional dependencies. In addition, our model employs a cross-attention-based architecture to capture the speaker style of the prompt voice and improves computational efficiency. Experimental results demonstrate that our proposed model outperforms the baselines in prompt-based audio generation.

eess.AS↗
arXiv2023

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. This letter proposes the EEND-DEMUX model, a novel framework utilizing demultiplexed speaker embeddings. In this work, we focus on disentangling speaker-relevant information in the latent space and then transform each separated latent variable into its corresponding speech activity. EEND-DEMUX can directly obtain separated speaker embeddings through the demultiplexing operation in the inference phase without an external speaker diarization system, an embedding extractor, or a heuristic decoding technique. Furthermore, we employ a multi-head cross-attention mechanism to capture the correlation between mixture and separated speaker embeddings effectively. We formulate three loss functions based on matching, orthogonality, and sparsity constraints to learn robust demultiplexed speaker embeddings. The experimental results on the LibriMix dataset show consistently improved performance in both a fixed and flexible number of speakers scenarios.

eess.AS↗
arXiv2023

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. We use discretized semantic tokens acquired from wav2vec2.0 embeddings, which makes it easy to adopt a neural transducer for the TTS framework enjoying its monotonic alignment constraints. The proposed model first generates aligned semantic tokens using the neural transducer, then synthesizes a speech sample from the semantic tokens using a non-autoregressive(NAR) speech generator. This decoupled framework alleviates the training complexity of TTS and allows each stage to focus on 1) linguistic and alignment modeling and 2) fine-grained acoustic modeling, respectively. Experimental results on the zero-shot adaptive TTS show that the proposed model exceeds the baselines in speech quality and speaker similarity via objective and subjective measures. We also investigate the inference speed and prosody controllability of our proposed model, showing the potential of the neural transducer for TTS frameworks.

eess.AS↗
arXiv2023

Oracle Teacher: Leveraging Target Information for Better Knowledge Distillation of CTC Models

Knowledge distillation (KD), best known as an effective method for model compression, aims at transferring the knowledge of a bigger network (teacher) to a much smaller network (student). Conventional KD methods usually employ the teacher model trained in a supervised manner, where output labels are treated only as targets. 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. Since the Oracle Teacher learns a more accurate CTC alignment by referring to the target information, it can provide the student with more optimal guidance. One potential risk for the proposed approach is a trivial solution that the model's output directly copies the target input. Based on a many-to-one mapping property of the CTC algorithm, we present a training strategy that can effectively prevent the trivial solution and thus enables utilizing both source and target inputs for model training. Extensive experiments are conducted on two sequence learning tasks: speech recognition and scene text recognition. From the experimental results, we empirically show that the proposed model improves the students across these tasks while achieving a considerable speed-up in the teacher model's training time.

cs.LG↗