* feat(face-landmarks): add timeline

* add duration to xmpp payload

Use the participant ID as the key to codecs, etc, instead of the source
name. The object is further indexed by SSRC.

Don't wait for both codecs to be set before propagating codec
information.

Sample data model for codecs:

codec: {
    participant1: {
        ssrc1: {
            audio: 'opus',
            video: undefined
        },
        ssrc2: {
            audio: undefined,
            video: 'VP8'
        },
        ...
    }
    ,...
}

Some values, like codecs, are available right away, we don't need to
compute differences.

This fixes an error that gets logged when no media is being sent/received by the endpoint.
Logger.js:154 2022-09-12T14:40:53.476Z [modules/statistics/AvgRTPStatsReporter.js] <xl.addNext>:  bandwidth_upload - invalid value for idx: 0

* fix(multi-stream): Fix local SSRC cache to include multiple video streams.
If multiple local video streams are found in the SDP, cache all of them instead of the first video SSRC. This fixes an issue where the resolution/fps stats for the screenshare track are not available.

* squash: new track inherits the source name of old track if it exists.

This allows us to display resolution and framerate stats on separate tiles when multi-stream mode is enabled.

* feat: facial expression in speaker stats

* feat: send xmpp message with facial expression to server

* fix: rebase conflicts

* feat: facial expression in speaker stats

* feat: facial expression in speaker stats

* fchore(facial-expressions): remove the send facial expression call from update facial expression function

* feat(facial-expressions): store expresions as a timeline

* refactor(facial-expressions): store expressions by counting them in a map

* feat(facial-expressions): camera time tracker

* add(facial-expression): increase facial expression with duration parameter from payload

* add(facial-expressions): the disgusted expression

* refactor(facial-expressions): remove camera time tracker

* refactor(facial-expressions): change data channel message handel position for facial expressions and renamed some types

* fix(facial-expressions): move facial expression endpoint message handler from statistics.js to ConnectionQuality.js

* fix(facial-expressions): remove unused type

* enable config callstats configParams

* add comments

* wrap long comments

* fix format

* fix format

* fix format

* add jsDoc

Switch to returning a Promise for getStats. Reset frame rate stat to 0 when video is suspended as a result of endpoint falling out of last-n.

Get rid of the browser specific keys and use the standard spec-compliant fields for stats.
Get the resolution/fps for remote streams from 'inbound-rtp' stats. Use the 'track' stats for the local resolution/fps since these take the active simulcast streams into account.

Capture the audio levels only for the top 5 speakers as RTCRtpReceiver#getSynchronizationSources can be expensive when we have too many audio receivers in the call.
Also, capture the audio levels for track that are unmuted if RTCRtpReceiver#getSynchronizationSources is not supported.
Switch Safari to using getStats since its reporting errorneous values, i.e., 0.000001 as audio level for all remote audio tracks.

Apple added getUserMedia support for WkWebview based browsers like chrome and Firefox on iOS 14.3. These browsers behave as Safari does on iOS. Therefore, extend the Safari checks to these webkit based browsers as well.

...which contains conference duration in seconds and
performance stats (currently long tasks).

Add a performance stat around long tasks. Chrome supports PerformanceObserver API that lets us
register for long tasks event. Any task that takes longer than 50ms is considered a long task.

The audio levels reported on the audio receivers are lower when compared to the value reported by getStats.
Values reported by getStats on chrome do not follow the the spec and since we have combination of clients using both getStats and getSynchronizationSources,
lets stick to one scale to make them look uniform.
Also, the receivers seem to be reporting audio level for a little bit after the remote user has muted. Make sure the track is unmuted
before setting the audio level on the track.

* feat: use getSynchronizationSources on the receiver for remote audio levels
Use getSynchronizationSources if it is supported, fallback to using getStats otherwise.
* feat/ref: Use the local audio levels from LocalStatsCollector
When using getSynchronizationSources, use the audio levels from LocalStatsCollector for NoAudioSignalDetection.js
Remove obsolete code - TalkMutedDetection feature using audio levels is not used anymore