arXiv subjects

Jinming Chen

Publications and source records attributed to Jinming Chen.

At least 19 recordsLinked to original sources

arXiv2026

JoyAI-Talker: Full-Duplex Speech Interactive Large Model Built for Empathetic Voice Agents

We present JoyAI-Talker, a full-duplex speech dialogue system that delivers robust foundation model capabilities while empowering empathetic interaction and voice agent intelligence. JoyAI-Talker adopts a modular Thinker-Talker architecture and further implements a unified speech-text joint training pipeline to mitigate the common "cognitive degradation" bottleneck, thereby largely preserving the model's core textual reasoning, STEM, and logical capabilities while extending them to speech-based interaction. For expressive speech synthesis, the Talker module employs a text-controllable generation paradigm that enables natural-language instructions to flexibly control vocal attributes and localized paralinguistic events, such as laughter and sighs, supporting more expressive and fine-grained speech responses. To enhance conversational empathy, we introduce the Persona-Adaptive Empathetic Response (PAER) framework. PAER employs a hierarchical cognitive pipeline to extract non-verbal speaker cues, such as gender, age, and emotional state, from raw input audio, incorporate them into the Thinker's CoT reasoning, and generate context-adaptive responses that align semantically appropriate text with fine-grained control over utterance-level expressiveness and localized paralinguistic events, including sighs, speaking rate, and volume. We further integrate Joy-Duplex, a state-driven, plug-and-play full-duplex framework that functions as an efficient gating engine for real-time turn control. Extensive evaluations show that JoyAI-Talker achieves highly competitive performance on foundational T2T and S2T benchmarks. In full-duplex evaluation, the system reaches a high response rate of 0.88 under user interruptions while maintaining an extremely low false-trigger rate under background speech, demonstrating its readiness for fluid and natural speech dialogue.

cs.SD↗

arXiv2026

Hybrid-Integrated DFB-Laser-Coupled 1 * 8 Thin-Film Lithium Niobate Modulator Array for High-Speed Parallel Optical Transmitters

Thin-film lithium niobate (TFLN) electro-optic modulators are attractive for high-speed optical interconnects, but scalable transmitter architectures require not only high modulation bandwidth but also multi-channel optical power distribution and practical laser-to-chip integration. Here, we demonstrate a hybrid-integrated 1 * 8 TFLN electro-optic modulator array passively butt-coupled to a 1550 nm distributed-feedback laser. The chip integrates a three-stage cascaded 1 * 2 multimode-interference splitter, spot-size converters, eight traveling-wave Mach-Zehnder modulators, thermal tuning electrodes, and on-chip 50 {\Omega} terminations. The cascaded splitter provides uniform optical power distribution with a maximum normalized power deviation of 9.7%, while the optimized electrodes enable electro-optic 3 dB bandwidths exceeding 40 GHz for all channels. The measured half-wave voltages are 3.60-3.83 V, corresponding to V{\pi}L products of 2.52-2.68 V cm for a 7 mm modulation length, and the extinction ratio reaches approximately 25 dB. The bare-chip insertion loss is 15.19-16.55 dB, and DFB laser bonding introduces an additional coupling loss of approximately 5 dB while preserving channel uniformity. These results establish a practical TFLN-based multi-channel modulator platform and represent a step toward compact hybrid-integrated optical transmitters for high-speed parallel interconnects.

physics.optics↗

arXiv2025

JoyVoice: Long-Context Conditioning for Anthropomorphic Multi-Speaker Conversational Synthesis

Large speech generation models are evolving from single-speaker, short sentence synthesis to multi-speaker, long conversation geneartion. Current long-form speech generation models are predominately constrained to dyadic, turn-based interactions. To address this, we introduce JoyVoice, a novel anthropomorphic foundation model designed for flexible, boundary-free synthesis of up to eight speakers. Unlike conventional cascaded systems, JoyVoice employs a unified E2E-Transformer-DiT architecture that utilizes autoregressive hidden representations directly for diffusion inputs, enabling holistic end-to-end optimization. We further propose a MM-Tokenizer operating at a low bitrate of 12.5 Hz, which integrates multitask semantic and MMSE losses to effectively model both semantic and acoustic information. Additionally, the model incorporates robust text front-end processing via large-scale data perturbation. Experiments show that JoyVoice achieves state-of-the-art results in multilingual generation (Chinese, English, Japanese, Korean) and zero-shot voice cloning. JoyVoice achieves top-tier results on both the Seed-TTS-Eval Benchmark and multi-speaker long-form conversational voice cloning tasks, demonstrating superior audio quality and generalization. It achieves significant improvements in prosodic continuity for long-form speech, rhythm richness in multi-speaker conversations, paralinguistic naturalness, besides superior intelligibility. We encourage readers to listen to the demo at https://jea-speech.github.io/JoyVoice

cs.SD↗

arXiv2025

Rad-GS: Radar-Vision Integration for 3D Gaussian Splatting SLAM in Outdoor Environments

We present Rad-GS, a 4D radar-camera SLAM system designed for kilometer-scale outdoor environments, utilizing 3D Gaussian as a differentiable spatial representation. Rad-GS combines the advantages of raw radar point cloud with Doppler information and geometrically enhanced point cloud to guide dynamic object masking in synchronized images, thereby alleviating rendering artifacts and improving localization accuracy. Additionally, unsynchronized image frames are leveraged to globally refine the 3D Gaussian representation, enhancing texture consistency and novel view synthesis fidelity. Furthermore, the global octree structure coupled with a targeted Gaussian primitive management strategy further suppresses noise and significantly reduces memory consumption in large-scale environments. Extensive experiments and ablation studies demonstrate that Rad-GS achieves performance comparable to traditional 3D Gaussian methods based on camera or LiDAR inputs, highlighting the feasibility of robust outdoor mapping using 4D mmWave radar. Real-world reconstruction at kilometer scale validates the potential of Rad-GS for large-scale scene reconstruction.

cs.CV↗

arXiv2025

Index-MSR: A high-efficiency multimodal fusion framework for speech recognition

Driven by large scale datasets and LLM based architectures, automatic speech recognition (ASR) systems have achieved remarkable improvements in accuracy. However, challenges persist for domain-specific terminology, and short utterances lacking semantic coherence, where recognition performance often degrades significantly. In this work, we present Index-MSR, an efficient multimodal speech recognition framework. At its core is a novel Multimodal Fusion Decoder (MFD), which effectively incorporates text-related information from videos (e.g., subtitles and presentation slides) into the speech recognition. This cross-modal integration not only enhances overall ASR accuracy but also yields substantial reductions in substitution errors. Extensive evaluations on both an in-house subtitle dataset and a public AVSR dataset demonstrate that Index-MSR achieves sota accuracy, with substitution errors reduced by 20,50%. These results demonstrate that our approach efficiently exploits text-related cues from video to improve speech recognition accuracy, showing strong potential in applications requiring strict audio text synchronization, such as audio translation.

eess.AS↗

arXiv2025

Qieemo: Speech Is All You Need in the Emotion Recognition in Conversations

Emotion recognition plays a pivotal role in intelligent human-machine interaction systems. Multimodal approaches benefit from the fusion of diverse modalities, thereby improving the recognition accuracy. However, the lack of high-quality multimodal data and the challenge of achieving optimal alignment between different modalities significantly limit the potential for improvement in multimodal approaches. In this paper, the proposed Qieemo framework effectively utilizes the pretrained automatic speech recognition (ASR) model backbone which contains naturally frame aligned textual and emotional features, to achieve precise emotion classification solely based on the audio modality. Furthermore, we design the multimodal fusion (MMF) module and cross-modal attention (CMA) module in order to fuse the phonetic posteriorgram (PPG) and emotional features extracted by the ASR encoder for improving recognition accuracy. The experimental results on the IEMOCAP dataset demonstrate that Qieemo outperforms the benchmark unimodal, multimodal, and self-supervised models with absolute improvements of 3.0%, 1.2%, and 1.9% respectively.

eess.AS↗

arXiv2024

Universal Wong formula for capture cross sections from light to super-heavy systems

A universal Wong formula is proposed with refined model parameters for a systematic description of the capture cross sections for heavy-ion fusion reactions from C+C to Ni+U, in which the barrier parameters and the barrier distribution are determined by the entrance-channel nucleus-nucleus potential based on the Skyrme energy density functional. With introducing a constraint to the width of the barrier distribution and a pocket-depth dependent barrier radius, the capture excitation functions for a number of fusion reactions involving different nuclear structure effects are remarkably well reproduced, particularly for the reactions between light nuclei and those forming super-heavy nuclei. The systematic decreasing behavior of the geometric radii with the depth of capture pocket due to the influence of deep inelastic scattering is clearly observed in the TDHF calculations for super-heavy systems. The predicted capture cross sections for $^{54}$Cr + $^{238}$U at above barrier energies are evidently smaller than the corresponding results of more asymmetric projectile-target combination $^{50}$Ti + $^{242}$Pu due to the shallower capture pocket in Cr+U.

nucl-th↗

arXiv2024

Effective nucleus-nucleus potentials for heavy-ion fusion reactions

Based on the Skyrme energy density functional and the reaction $Q$-value, we propose an effective nucleus-nucleus potential for describing the capture barrier in heavy-ion fusion processes. The 443 extracted barrier heights are well reproduced with a root-mean-square (rms) error of 1.53 MeV and the rms deviations with respect to 144 TDHF capture barrier heights is only 1.05 MeV. Together with the Siwek-Wilczyński formula in which the three parameters are determined by the proposed effective potentials, the measured capture cross sections at energies around the barriers can be reasonably well reproduced for a series of fusion reactions induced by not only nearly spherical nuclei but also the nuclei with large deformations such as $^{154}$Sm and $^{238}$U. The shallow capture pockets and small values of the average barrier radii play a role in the reduction of the capture cross sections for $^{52,54}$Cr and $^{64}$Ni induced reactions which are related to the synthesis of new super-heavy nuclei.

nucl-th↗

arXiv2024

Frequency stabilization based on H13C14N absorption in lithium niobate micro-disk laser

We demonstrate an on-chip lithium niobate micro-disk laser based on hydrogen cyanide (H13C14N) gas saturation absorption method for frequency stabilization. The laser chip consists of two main components: a micro-disk laser and a combined racetrack ring cavity. By operating on the H13C14N P12 absorption line at 1551.3 nm, the laser frequency can be precisely stabilized. The laser demonstrates remarkable stability, achieving a best stability value of 9*10^-9. Furthermore, the short-term stability, evaluated over continuous time intervals of 35 seconds, showcases exceptional performance. Additionally, the residual drift remains well below 30 MHz.

physics.optics↗

arXiv2024

Qifusion-Net: Layer-adapted Stream/Non-stream Model for End-to-End Multi-Accent Speech Recognition

Currently, end-to-end (E2E) speech recognition methods have achieved promising performance. However, auto speech recognition (ASR) models still face challenges in recognizing multi-accent speech accurately. We propose a layer-adapted fusion (LAF) model, called Qifusion-Net, which does not require any prior knowledge about the target accent. Based on dynamic chunk strategy, our approach enables streaming decoding and can extract frame-level acoustic feature, facilitating fine-grained information fusion. Experiment results demonstrate that our proposed methods outperform the baseline with relative reductions of 22.1$\%$ and 17.2$\%$ in character error rate (CER) across multi accent test datasets on KeSpeech and MagicData-RMAC.

cs.SD↗

arXiv2024

An integrated electro-optically tunable multi-channel interference cavity laser

We demonstrated a continuously tunable laser system by butt coupling a reflective semiconductor optical amplifier (RSOA) chip with a thin-film lithium niobate (TFLN) based multi-channel interference (MCI) cavity chip. This hybrid integrated lasers allows for fine-tuning of the laser wavelength from 1538 nm to 1560 nm with a resolution of 0.014 nm and a side-mode suppression ratio (SMSR) exceeding 30 dB. The MCI cavity chip is fabricated using the photolithography assisted chemo-mechanical etching (PLACE) technique. The developed laser has an output power of approximately 10 μW, which can be further amplified to 70 mW using a commercial erbium-doped fiber amplifier (EDFA) without significant broadening of the laser linewidth.

physics.optics↗

arXiv2024

Compact low-half-wave-voltage thin film lithium niobate electro-optic phase modulator fabricated by photolithography assisted chemo-mechanical etching

This paper presents a compact dual-arm thin film lithium niobate (TFLN) electro-optic phase modulator fabricated using the photolithography-assisted chemo-mechanical etching (PLACE) technique. The design of the device allows for complete utilization of the microwave electric field, doubling the modulation efficiency compared to single-arm modulators in theory. With a half-wave voltage of approximately 3 V and a modulation length of 1 cm, the device outperforms conventional phase modulators. Furthermore, the phase modulator exhibits low sensitivity to optical wavelengths in the range of 1510-1600 nm and offers a low insertion loss of 2.8 dB. The capability to generate multiple sideband signals for optical frequency comb applications is also demonstrated, producing 29 sideband signals at an input microwave power of 2 W.

physics.optics↗

arXiv2024

An erbium-doped waveguide amplifier on thin film lithium niobate with an output power exceeding 100 mW

We demonstrate high-power thin film lithium niobate (TFLN) erbium-doped waveguide amplifier (EDWA) with a maximum on-chip output power of 113 mW and a gain of 16 dB. The on-chip integrated EDWA is composed of large mode area (LMA) waveguide structures with a total length of 7 cm and a footprint of 1x1 cm2. Particularly, we connect segmented LMA waveguides with waveguide tapers to achieve on-chip mode conversion which maintains single-mode propagation all over the EDWA even at the waveguide bends. The design leads to significant increase of the amplified signal power by orders of magnitude and will open an avenue for applications such as on-chip high-power lasers and amplifiers system.

physics.optics↗

arXiv2023

Thin Film Lithium Niobate Electro-optic Isolator Fabricated by photolithography assisted chemo-mechanical etching (PLACE)

We report a thin-film lithium niobate electro-optic isolator fabricated by photolithography-assisted chemo-mechanical etching in this work. The device demonstrates 39.50 dB isolation when subjected to a 24 GHz microwave of 25.5 dBm on its electrodes. The measured isolation remains consistently above 30 dB within the 1510 nm to 1600 nm wavelength range. The overall device insertion loss, specifically the fiber-to-fiber insert loss, has been measured to be 2.6 dB, which is attributed to our highly efficient spot size converter and the low propagation loss observed in the fabricated waveguides.

physics.optics↗

arXiv2023

Electro-optically programmable photonic circuits enabled by wafer-scale integration on thin-film lithium niobate

Programmable photonic circuits performing universal linear-optical transformations underpin vital functions in photonic quantum information processing, quantum-enhanced sensor networks, machine learning and many other intriguing applications. Recent advances in photonic integrated circuits facilitate monolithic integration of externally controlled Mach-Zehnder interferometers which can implement arbitrary unitary transformation on a large number of input/output modes. In this work, we demonstrate a 4x4 programmable linear photonic circuit on lithium niobate on insulator platform employing fast, power-efficient and low-loss electro-optical phase shifters, showing enormous advantages in terms of configuration rate and power consumption. Our device is capable of fast switching with 500 ps rise time and 1.7 ns fall time, and possesses a total on-chip power dissipation of only 0.015 mW when operated at 1 MHz modulation, and an insertion loss of 0.15 dB for each modulator and an on-chip extinction ratio of -34 dB for both cross and bar routes.

physics.optics↗

arXiv2023

Ultra-high-speed high-resolution laser lithography for lithium niobate integrated photonics

Photolithography assisted chemo-mechanical etching (PLACE), a technique specifically developed for fabricating highquality large-scale photonic integrated circuits (PICs) on thin-film lithium niobate (TFLN), has enabled fabrication of a series of building blocks of PICs ranging from high-quality (high-Q) microresonators and low-loss waveguides to electrooptically (EO) tunable lasers and waveguide amplifiers. Aiming at high-throughput manufacturing of the PIC devices and systems, we have developed an ultra-high-speed high-resolution laser lithography fabrication system employing a high repetition rate femtosecond laser and a high-speed polygon laser scanner, by which a lithography fabrication efficiency of 4.8 cm2/h has been achieved at a spatial resolution of 200 nm. We demonstrate wafer-scale fabrication of TFLN-based photonic structures, optical phase masks as well as color printing

physics.optics↗

arXiv2021

Photon retention in coherently excited nitrogen ions

Quantum coherence in quantum optics is an essential part of optical information processing and light manipulation. Alkali metal vapors, despite the numerous shortcomings, are traditionally used in quantum optics as a working medium due to convenient near-infrared excitation, strong dipole transitions and long-lived coherence. Here, we proposed and experimentally demonstrated photon retention and subsequent re-emittance with the quantum coherence in a system of coherently excited molecular nitrogen ions (N2+) which are produced using a strong 800 nm femtosecond laser pulse. Such photon retention, facilitated by quantum coherence, keeps releasing directly-unmeasurable coherent photons for tens of picoseconds, but is able to be read-out by a time-delayed femtosecond pulse centered at 1580 nm via two-photon resonant absorption, resulting in a strong radiation at 329.3 nm. We reveal a pivotal role of the excited-state population to transmit such extremely weak re-emitted photons in this system. This new finding unveils the nature of the coherent quantum control in N2+ for the potential platform for optical information storage in the remote atmosphere, and facilitates further exploration of fundamental interactions in the quantum optical platform with strong-field ionized molecules.

quant-ph↗

arXiv2020

A spectrally bright wavelength-switchable vacuum ultraviolet source driven by quantum coherence in strong-field-ionized molecules

We report generation of spectrally bright vacuum ultraviolet (VUV) and deep UV (DUV) coherent radiations driven by quantum coherence in tunnel-ionized carbon monoxide (CO) molecules. Our technique allows us to switch between multiple wavelengths provided by the abundant energy levels of molecular ions. The DUV/VUV sources can have arbitrary polarization states by manipulating the pump laser polarization. The superior temporal and spectral properties of the developed source give rise to a broadband Raman comb in the DUV/VUV region.

physics.optics↗