# US 2026/0065899 A1 · Method and apparatus for evaluating speech quality

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0065899 A1
- Document ID: US20260065899A1
- Status: Published application
- Kind: A1
- Application number: 19/314,809
- Filed: 2025-08-29
- Published: 2026-03-05
- Earliest claimed: 2024-08-30
- Assignees: Hyundai Motor Company; Kia Corporation; UIF (University Industry Foundation), Yonsei University
- Applicants: Hyundai Motor Company; Kia Corporation; UIF (University Industry Foundation), Yonsei University
- Inventors: Sung Woong Hwang; Soo Joong Hwang; Chang Hwan Kim; Se Yun Um; Woo Seok Ko; Hong Goo Kang; Ju Hwan Yoon
- Web page: https://patentgrep.com/patent/US20260065899A1

## CPC

- G10L 15/01: Assessment or evaluation of speech recognition systems
- G10L 25/69: for evaluating synthetic or decoded voice signals
- G10L 15/063: {Training}
- G10L 25/30: using neural networks
- G10L 2015/0631: {Creating reference templates; Clustering}
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

In an embodiment a method for evaluating speech quality includes receiving, by a computing device, synthesized speech comprising one or more frames, determining, by the computing device, a latent representation corresponding to each frame, clustering, by the computing device, each latent representation and then mapping a center point of each cluster to an index to determine a centroid index sequence, determining, by the computing device, an embedding sequence by replacing each index of the centroid index sequence with an embedding corresponding to each index, and then masking one or more of embeddings, determining, by the computing device, a predicted index sequence that reconstructs a masked embedding based on a masked embedding sequence, and determining, by the computing device, an evaluation score based on a difference between the centroid index sequence and the predicted index sequence.

## Claims

### Claim 1

A method for evaluating speech quality, the method comprising:
receiving, by a computing device, synthesized speech comprising one or more frames;
determining, by the computing device, a latent representation corresponding to each frame;
clustering, by the computing device, each latent representation and then mapping a center point of each cluster to an index to determine a centroid index sequence;
determining, by the computing device, an embedding sequence by replacing each index of the centroid index sequence with an embedding corresponding to each index, and then masking one or more of embeddings;
determining, by the computing device, a predicted index sequence that reconstructs a masked embedding based on a masked embedding sequence; and
determining, by the computing device, an evaluation score based on a difference between the centroid index sequence and the predicted index sequence.

### Claim 2 (depends on 1)

The method of claim 1, wherein the latent representation is extracted using a machine learning model that has pre-trained referenced speech using a self-supervised learning method.

### Claim 3 (depends on 1)

The method of claim 1, wherein clustering uses a k-means clustering algorithm.

### Claim 4 (depends on 1)

The method of claim 1, wherein masking is performed by randomly selecting one embedding from the embedding sequences and replacing five consecutive embeddings starting from the selected embedding with the one embedding.

### Claim 5 (depends on 1)

The method of claim 1, wherein the predicted index sequence is estimated using a machine learning model that has pre-trained a feature distribution of referenced speech using an unsupervised learning method.

### Claim 6 (depends on 1)

The method of claim 1, wherein determining the evaluation score comprises determining a loss value between the centroid index sequence and the predicted index sequence using a cross-entropy loss function.

### Claim 7 (depends on 1)

The method of claim 1, further comprising determining an integrated score that evaluates multidimensional speech quality by integrating a plurality of evaluation scores determined based on latent representations corresponding to different acoustic features.

### Claim 8 (depends on 1)

The method of claim 1, wherein determining the latent representation corresponding to each frame comprises extracting acoustic information from a sixth layer and linguistic information from a twenty-third layer of a transformer encoder.

### Claim 9 (depends on 1)

The method of claim 1, wherein clustering each latent representation comprises discretizing the latent representation into 1024 clusters.

### Claim 10

A method for training a speech quality evaluation method, the method comprising:
receiving, by a computing device, referenced speech comprising one or more frames;
determining, by the computing device, a latent representation corresponding to each frame;
clustering, by the computing device, each latent representation, and then mapping a center point of each cluster to an index to determine a centroid index sequence;
determining, by the computing device, an embedding sequence by replacing each index of the centroid index sequence with an embedding corresponding to each index, and then masking one or more of the embeddings;
determining, by the computing device, a predicted index sequence that reconstructs a masked embedding based on a masked embedding sequence, using a machine learning model that has pre-trained a feature distribution of the referenced speech using an unsupervised learning method;
determining, by the computing device, a loss value between the centroid index sequence and the predicted index sequence; and
updating, by the computing device, a parameter of the machine learning model based on the loss value.

### Claim 11

An apparatus comprising:
one or more processors; and
at least one memory storing a program including program instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
receiving synthesized speech comprising one or more frames;
determining a latent representation corresponding to each frame;
clustering each latent representation, and then mapping a center point of each cluster to an index to determine a centroid index sequence;
determining an embedding sequence by replacing each index of the centroid index sequence with an embedding corresponding to each index, and then masking one or more of embeddings;
determining a predicted index sequence that reconstructs a masked embedding based on a masked embedding sequence; and
determining an evaluation score based on a difference between the centroid index sequence and the predicted index sequence.

### Claim 12 (depends on 11)

The apparatus of claim 11, wherein the latent representation is extracted using a machine learning model that has pre-trained referenced speech using a self-supervised learning method.

### Claim 13 (depends on 11)

The apparatus of claim 11, wherein clustering uses a k-means clustering algorithm.

### Claim 14 (depends on 11)

The apparatus of claim 11, wherein masking is performed by randomly selecting one embedding from the embedding sequences and replacing five consecutive embeddings starting from the selected embedding with the one embedding.

### Claim 15 (depends on 11)

The apparatus of claim 11, wherein the predicted index sequence is estimated using a machine learning model that has pre-trained a feature distribution of referenced speech using an unsupervised learning method.

### Claim 16 (depends on 11)

The apparatus of claim 11, wherein determining the evaluation score comprises determining a loss value between the centroid index sequence and the predicted index sequence using a cross-entropy loss function.

### Claim 17 (depends on 11)

The apparatus of claim 11, wherein the operations further comprises determining an integrated score that evaluates multidimensional speech quality by integrating a plurality of evaluation scores determined based on latent representations corresponding to different acoustic features.

### Claim 18 (depends on 11)

The apparatus of claim 11, wherein determining the latent representation corresponding to each frame comprises extracting acoustic information from a sixth layer and linguistic information from a twenty-third layer of a transformer encoder.

### Claim 19 (depends on 11)

The apparatus of claim 11, wherein clustering each latent representation comprises discretizing the latent representation into 1024 clusters.

### Claim 20

An apparatus comprising:
one or more processors; and
at least one memory storing a program including program instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
receiving referenced speech including one or more frames;
determining a latent representation corresponding to each frame;
clustering each latent representation, and then mapping a center point of each cluster to an index to determine a centroid index sequence;
determining an embedding sequence by replacing each index of the centroid index sequence with an embedding corresponding to each index, and then masking one or more of the embeddings;
determining a predicted index sequence that reconstructs a masked embedding based on a masked embedding sequence, using a machine learning model that has pre-trained a feature distribution of the referenced speech using an unsupervised learning method;
determining a loss value between the centroid index sequence and the predicted index sequence; and
updating a parameter of the machine learning model based on the loss value.
